Shay Moran

NeurIPS Conference 2025 Conference Paper

Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness

• Bogdan Chornomaz
• Yonatan Koren
• Shay Moran
• Tom Waknine

We study the problem of learning in the presence of an adversary that can corrupt an $\eta$ fraction of the training examples with the goal of causing failure on a specific test point. In the realizable setting, prior work established that the optimal error under such instance-targeted poisoning attacks scales as $\Theta(d\eta)$, where $d$ is the VC dimension of the hypothesis class [Hanneke, Karbasi, Mahmoody, Mehalel, and Moran (NeurIPS 2022)]. In this work, we resolve the corresponding question in the agnostic setting. We show that the optimal excess error is $\widetilde\Theta(\sqrt{d\eta})$, answering one of the main open problems left by Hanneke et al. To achieve this rate, it is necessary to use randomized learners: Hanneke et al. \ showed that deterministic learners can be forced to suffer error close to $1$ even under small amounts of poisoning. Perhaps surprisingly, our upper bound remains valid even when the learner’s random bits are fully visible to the adversary. In the other direction, our lower bound is stronger than standard PAC-style bounds: instead of tailoring a hard distribution separately for each sample size, we exhibit a single fixed distribution under which the adversary can enforce an excess error of $\Omega(\sqrt{d\eta})$ infinitely often.

NeurIPS Conference 2025 Conference Paper

Marginal-Nonuniform PAC Learnability

• Steve Hanneke
• Shay Moran
• Maximilian Thiessen

We revisit the classical model of nonuniform PAC learning, introduced by Benedek and Itai [1994], where generalization guarantees may depend on the target concept (but not on the marginal distribution). In this work, we study a complementary variant, which we call *marginal-nonuniform learning*. In this setting, guarantees may depend on the marginal distribution over the domain, but must hold uniformly over all concepts. This captures the intuition that some data distributions are inherently easier to learn from than others, allowing for a flexible, distribution-sensitive view of learnability. Our main result is a complete characterization of the achievable learning rates in this model, revealing a trichotomy: exponential rates of the form $e^{-n}$ arise precisely when the hypothesis class is finite; linear rates of the form $d/n$ are achievable when a recently introduced combinatorial parameter, the VC-eluder dimension $d$, is finite; and arbitrarily slow rates may occur when $d = \infty$. Additionally, in the original (concept-)nonuniform model, we show that for all learnable classes linear rates are achievable. We conclude by situating marginal-nonuniform learning within the landscape of universal learning, and by discussing its relationship to other distribution-dependent learning paradigms.

STOC Conference 2025 Conference Paper

On Differentially Private Linear Algebra

• Haim Kaplan
• Yishay Mansour
• Shay Moran
• Uri Stemmer
• Nitzan Tur

We introduce efficient differentially private (DP) algorithms for several linear algebraic tasks, including solving linear equalities over arbitrary fields, linear inequalities over the reals, and computing affine spans and convex hulls. As an application, we obtain efficient DP algorithms for learning halfspaces and affine subspaces. Our algorithms addressing equalities are strongly polynomial, whereas those addressing inequalities are weakly polynomial. Furthermore, this distinction is inevitable: no DP algorithm for linear programming can be strongly polynomial-time efficient.

STOC Conference 2025 Conference Paper

On Reductions and Representations of Learning Problems in Euclidean Spaces

• Bogdan Chornomaz
• Shay Moran
• Tom Waknine

Many practical prediction algorithms represent inputs in Euclidean space and replace the discrete 0/1 classification loss with a real-valued surrogate loss, effectively reducing classification tasks to stochastic optimization. In this paper, we investigate the expressivity of such reductions in terms of key resources, including dimension and the role of randomness. We establish bounds on the minimum Euclidean dimension D needed to reduce a concept class with VC dimension d to a Stochastic Convex Optimization (SCO) problem in ℝ D , formally addressing the intuitive interpretation of the VC dimension as the number of parameters needed to learn the class. To achieve this, we develop a generalization of the Borsuk-Ulam Theorem that combines the classical topological approach with convexity considerations. Perhaps surprisingly, we show that, in some cases, the number of parameters D must be exponentially larger than the VC dimension d , even if the reduction is only slightly non-trivial. We also present natural classification tasks that can be represented in much smaller dimensions by leveraging randomness, as seen in techniques like random initialization. This result resolves an open question posed by Kamath, Montasser, and Srebro (COLT 2020). Our findings introduce new variants of dimension complexity (also known as sign-rank ), a well-studied parameter in learning and complexity theory. Specifically, we define an approximate version of sign-rank and another variant that captures the minimum dimension required for a reduction to SCO. We also propose several open questions and directions for future research.

NeurIPS Conference 2025 Conference Paper

Optimal Mistake Bounds for Transductive Online Learning

• Zachary Chase
• Steve Hanneke
• Shay Moran
• Jonathan Shafer

We resolve a 30-year-old open problem concerning the power of unlabeled data in online learning by tightly quantifying the gap between transductive and standard online learning. We prove that for every concept class $\mathcal{H}$ with Littlestone dimension $d$, the transductive mistake bound is at least $\Omega(\sqrt{d})$. This establishes an exponential improvement over previous lower bounds of $\Omega(\log \log d)$, $\Omega(\sqrt{\log d})$, and $\Omega(\log d)$, respectively due to Ben-David, Kushilevitz, and Mansour (1995, 1997) and Hanneke, Moran, and Shafer (2023). We also show that our bound is tight: for every $d$, there exists a class of Littlestone dimension $d$ with transductive mistake bound $O(\sqrt{d})$. Our upper bound also improves the previous best known upper bound of $(2/3) \cdot d$ from Ben-David et al. (1997). These results demonstrate a quadratic gap between transductive and standard online learning, thereby highlighting the benefit of advanced access to the unlabeled instance sequence. This stands in stark contrast to the PAC setting, where transductive and standard learning exhibit similar sample complexities.

NeurIPS Conference 2025 Conference Paper

Probably Approximately Precision and Recall Learning

• Lee Cohen
• Yishay Mansour
• Shay Moran
• Han Shao

Precision and Recall are fundamental metrics in machine learning tasks where both accurate predictions and comprehensive coverage are essential, such as in multi-label learning, language generation, medical studies, and recommender systems. A key challenge in these settings is the prevalence of one-sided feedback, where only positive examples are observed during training—e. g. , in multi-label tasks like tagging people in Facebook photos, we may observe only a few tagged individuals, without knowing who else appears in the image. To address learning under such partial feedback, we introduce a Probably Approximately Correct (PAC) framework in which hypotheses are set functions that map each input to a set of labels, extending beyond single-label predictions and generalizing classical binary, multi-class, and multi-label models. Our results reveal sharp statistical and algorithmic separations from standard settings: classical methods such as Empirical Risk Minimization provably fail, even for simple hypothesis classes. We develop new algorithms that learn from positive data alone, achieving optimal sample complexity in the realizable case, and establishing multiplicative—rather than additive—approximation guarantees in the agnostic case, where achieving additive regret is impossible.

NeurIPS Conference 2025 Conference Paper

Reconstruction and Secrecy under Approximate Distance Queries

• Shay Moran
• Elizaveta Nesterova

Consider the task of locating an unknown target point using approximate distance queries: in each round, a reconstructor selects a reference point and receives a noisy version of its distance to the target. This problem arises naturally in various contexts—from localization in GPS and sensor networks to privacy-aware data access—making it relevant from the perspective of both the reconstructor (seeking accurate recovery) and the responder (aiming to limit information disclosure, e. g. , for privacy or security reasons). We study this reconstruction game through a learning-theoretic lens, focusing on the rate and limits of the best possible reconstruction error. Our first result provides a tight geometric characterization of the optimal error in terms of the Chebyshev radius, a classical concept from geometry. This characterization applies to all compact metric spaces (in fact, to all totally bounded spaces) and yields explicit formulas for natural subsets of the Euclidean metric. Our second result addresses the asymptotic behavior of reconstruction, distinguishing between pseudo-finite spaces, where the optimal error is attained after finitely many queries, and spaces where the approximation curve exhibits a nontrivial decay. We characterize pseudo-finiteness for convex subsets of Euclidean spaces.

ICML Conference 2025 Conference Paper

The Role of Randomness in Stability

• Max Hopkins
• Shay Moran

Stability is a central property in learning and statistics promising the output of an algorithm $\mathcal{A}$ does not change substantially when applied to similar datasets $S$ and $S’$. It is an elementary fact that any sufficiently stable algorithm (e. g. one returning the same result with high probability, satisfying privacy guarantees, etc.) must be randomized. This raises a natural question: can we quantify how much randomness is needed for algorithmic stability? We study the randomness complexity of two influential notions of stability in learning: replicability (which promises $\mathcal{A}$ usually outputs the same result when run over samples from the same distribution), and differential privacy (which promises the output distribution of $\mathcal{A}$ remains similar under neighboring datasets). In particular, building on the ideas of (Dixon, Pavan, Vander Woude, and Vinodchandran ICML 2024) and (Cannone, Su, and Vadhan ITCS 2024), we prove a "weak-to-strong" boosting theorem for stability in these settings: the randomness complexity of a task $\mathcal{M}$ is tightly controlled by the best replication probability of any deterministic algorithm solving $\mathcal{M}$, a parameter known as $\mathcal{M}$’s "global stability" (Chase, Moran, Yehudayoff FOCS 2023). Finally, we use this connection to characterize the randomness complexity of PAC Learning: a class has bounded randomness complexity iff it has finite Littlestone dimension, and moreover scales at worst logarithmically in the excess error of the learner. As a corollary, we resolve a question of (Chase, Chornomaz, Moran, and Yehudayoff STOC 2024) about the error-dependent list-replicability of agnostic learning.

NeurIPS Conference 2024 Conference Paper

Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs

• Yuval Filmus
• Steve Hanneke
• Idan Mehalel
• Shay Moran

Consider the domain of multiclass classification within the adversarial online setting. What is the price of relying on bandit feedback as opposed to full information? To what extent can an adaptive adversary amplify the loss compared to an oblivious one? To what extent can a randomized learner reduce the loss compared to a deterministic one? We study these questions in the mistake bound model and provide nearly tight answers. We demonstrate that the optimal mistake bound under bandit feedback is at most $O(k)$ times higher than the optimal mistake bound in the full information case, where $k$ represents the number of labels. This bound is tight and provides an answer to an open question previously posed and studied by Daniely and Helbertal ['13] and by Long ['17, '20], who focused on deterministic learners. Moreover, we present nearly optimal bounds of $\tilde{\Theta}(k)$ on the gap between randomized and deterministic learners, as well as between adaptive and oblivious adversaries in the bandit feedback setting. This stands in contrast to the full information scenario, where adaptive and oblivious adversaries are equivalent, and the gap in mistake bounds between randomized and deterministic learners is a constant multiplicative factor of $2$. In addition, our results imply that in some cases the optimal randomized mistake bound is approximately the square-root of its deterministic parallel. Previous results show that this is essentially the smallest it can get. Some of our results are proved via a reduction to prediction with expert advice under bandit feedback, a problem interesting on its own right. For this problem, we provide a randomized algorithm which is nearly optimal in some scenarios.

NeurIPS Conference 2024 Conference Paper

Credit Attribution and Stable Compression

• Roi Livni
• Shay Moran
• Kobbi Nissim
• Chirag Pabbaraju

Credit attribution is crucial across various fields. In academic research, proper citation acknowledges prior work and establishes original contributions. Similarly, in generative models, such as those trained on existing artworks or music, it is important to ensure that any generated content influenced by these works appropriately credits the original creators. We study credit attribution by machine learning algorithms. We propose new definitions--relaxations of Differential Privacy--that weaken the stability guarantees for a designated subset of $k$ datapoints. These $k$ datapoints can be used non-stably with permission from their owners, potentially in exchange for compensation. Meanwhile, the remaining datapoints are guaranteed to have no significant influence on the algorithm's output. Our framework extends well-studied notions of stability, including Differential Privacy ($k = 0$), differentially private learning with public data (where the $k$ public datapoints are fixed in advance), and stable sample compression (where the $k$ datapoints are selected adaptively by the algorithm). We examine the expressive power of these stability notions within the PAC learning framework, provide a comprehensive characterization of learnability for algorithms adhering to these principles, and propose directions and questions for future research.

NeurIPS Conference 2024 Conference Paper

Fast Rates for Bandit PAC Multiclass Classification

• Liad Erez
• Alon Cohen
• Tomer Koren
• Yishay Mansour
• Shay Moran

We study multiclass PAC learning with bandit feedback, where inputs are classified into one of $K$ possible labels and feedback is limited to whether or not the predicted labels are correct. Our main contribution is in designing a novel learning algorithm for the agnostic $(\varepsilon, \delta)$-PAC version of the problem, with sample complexity of $O\big( (\operatorname{poly}(K) + 1 / \varepsilon^2) \log (|\mathcal{H}| / \delta) \big)$ for any finite hypothesis class $\mathcal{H}$. In terms of the leading dependence on $\varepsilon$, this improves upon existing bounds for the problem, that are of the form $O(K/\varepsilon^2)$. We also provide an extension of this result to general classes and establish similar sample complexity bounds in which $\log |\mathcal{H}|$ is replaced by the Natarajan dimension. This matches the optimal rate in the full-information version of the problem and resolves an open question studied by Daniely, Sabato, Ben-David, and Shalev-Shwartz (2011) who demonstrated that the multiplicative price of bandit feedback in realizable PAC learning is $\Theta(K)$. We complement this by revealing a stark contrast with the agnostic case, where the price of bandit feedback is only $O(1)$ as $\varepsilon \to 0$. Our algorithm utilizes a stochastic optimization technique to minimize a log-barrier potential based on Frank-Wolfe updates for computing a low-variance exploration distribution over the hypotheses, and is made computationally efficient provided access to an ERM oracle over $\mathcal{H}$.

NeurIPS Conference 2024 Conference Paper

Improved Sample Complexity for Multiclass PAC Learning

• Steve Hanneke
• Shay Moran
• Qian Zhang

We aim to understand the optimal PAC sample complexity in multiclass learning. While finiteness of the Daniely-Shalev-Shwartz (DS) dimension has been shown to characterize the PAC learnability of a concept class [Brukhim, Carmon, Dinur, Moran, and Yehudayoff, 2022], there exist polylog factor gaps in the leading term of the sample complexity. In this paper, we reduce the gap in terms of the dependence on the error parameter to a single log factor and also propose two possible routes towards completely resolving the optimal sample complexity, each based on a key open question we formulate: one concerning list learning with bounded list size, the other concerning a new type of shifting for multiclass concept classes. We prove that a positive answer to either of the two questions would completely resolve the optimal sample complexity up to log factors of the DS dimension.

NeurIPS Conference 2024 Conference Paper

Learning-Augmented Algorithms with Explicit Predictors

• Marek Eliáš
• Haim Kaplan
• Yishay Mansour
• Shay Moran

Recent advances in algorithmic design show how to utilize predictions obtained by machine learning models from past and present data. These approaches have demonstrated an enhancement in performance when the predictions are accurate, while also ensuring robustness by providing worst-case guarantees when predictions fail. In this paper we focus on online problems; prior research in this context was focused on a paradigm where the algorithms are oblivious of the predictors' design, treating them as a black box. In contrast, in this work, we unpack the predictor and integrate the learning problem it gives rise for within the algorithmic challenge. In particular we allow the predictor to learn as it receives larger parts of the input, with the ultimate goal of designing online learning algorithms specifically tailored for the algorithmic task at hand. Adopting this perspective, we focus on a number of fundamental problems, including caching and scheduling, which have been well-studied in the black-box setting. For each of the problems, we introduce new algorithms that take advantage of explicit and carefully designed learning rules. These pairings of online algorithms with corresponding learning rules yields improvements in the overall performance in comparison with previous work.

STOC Conference 2024 Conference Paper

Local Borsuk-Ulam, Stability, and Replicability

• Zachary Chase 0001
• Bogdan Chornomaz
• Shay Moran
• Amir Yehudayoff

We use and adapt the Borsuk-Ulam Theorem from topology to derive limitations on list-replicable and globally stable learning algorithms. We further demonstrate the applicability of our methods in combinatorics and topology. We show that, besides trivial cases, both list-replicable and globally stable learning are impossible in the agnostic PAC setting. This is in contrast with the realizable case where it is known that any class with a finite Littlestone dimension can be learned by such algorithms. In the realizable PAC setting, we sharpen previous impossibility results and broaden their scope. Specifically, we establish optimal bounds for list replicability and global stability numbers in finite classes. This provides an exponential improvement over previous works and implies an exponential separation from the Littlestone dimension. We further introduce lower bounds for weak learners, i.e., learners that are only marginally better than random guessing. Lower bounds from previous works apply only to stronger learners. To offer a broader and more comprehensive view of our topological approach, we prove a local variant of the Borsuk-Ulam theorem in topology and a result in combinatorics concerning Kneser colorings. In combinatorics, we prove that if c is a coloring of all non-empty subsets of [ n ] such that disjoint sets have different colors, then there is a chain of subsets that receives at least 1+ ⌊ n /2⌋ colors (this bound is sharp). In topology, we prove e.g. that for any open antipodal-free cover of the d -dimensional sphere, there is a point ‍ x that belongs to at least t =⌈ d +3/2⌉ sets.

FOCS Conference 2024 Conference Paper

Ramsey Theorems for Trees and a General 'Private Learning Implies Online Learning' Theorem

• Simone Fioravanti
• Steve Hanneke
• Shay Moran
• Hilla Schefler
• Iska Tsubari

This work continues to investigate the link between differentially private (DP) and online learning. Alon, Livni, Malliaris, and Moran [4] showed that for binary concept classes, DP learnability of a given class implies that it has a finite Littlestone dimension (equivalently, that it is online learnable). Their proof relies on a model-theoretic result by Hodges [36], which demonstrates that any binary concept class with a large Littlestone dimension contains a large subclass of thresholds. In a follow-up work, Jung, Kim, and Tewari [38] extended this proof to multiclass PAC learning with a bounded number of labels. Unfortunately, Hodges's result does not apply in other natural settings such as multiclass PAC learning with an unbounded label space, and PAC learning of partial concept classes. This naturally raises the question of whether DP learnability continues to imply online learnability in more general scenarios: indeed, Alon, Hanneke, Holzman, and Moran [5] explicitly leave it as an open question in the context of partial concept classes, and the same question is open in the general multiclass setting. In this work, we give a positive answer to these questions showing that for general classification tasks, DP learnability implies online learnability. Our proof reasons directly about Littlestone trees, without relying on thresholds. We achieve this by establishing several Ramsey-type theorems for trees, which might be of independent interest.

NeurIPS Conference 2024 Conference Paper

Universal Rates for Active Learning

• Steve Hanneke
• Amin Karbasi
• Shay Moran
• Grigoris Velegkas

In this work we study the problem of actively learning binary classifiers from a given concept class, i. e. , learning by utilizing unlabeled data and submitting targeted queries about their labels to a domain expert. We evaluate the quality of our solutions by considering the learning curves they induce, i. e. , the rate of decrease of the misclassification probability as the number of label queries increases. The majority of the literature on active learning has focused on obtaining uniform guarantees on the error rate which are only able to explain the upper envelope of the learning curves over families of different data-generating distributions. We diverge from this line of work and we focus on the distribution-dependent framework of universal learning whose goal is to obtain guarantees that hold for any fixed distribution, but do not apply uniformly over all the distributions. We provide a complete characterization of the optimal learning rates that are achievable by algorithms that have to specify the number of unlabeled examples they use ahead of their execution. Moreover, we identify combinatorial complexity measures that give rise to each case of our tetrachotomic characterization. This resolves an open question that was posed by Balcan et al. (2010). As a byproduct of our main result, we develop an active learning algorithm for partial concept classes that achieves exponential learning rates in the uniform setting.

NeurIPS Conference 2023 Conference Paper

A Trichotomy for Transductive Online Learning

• Steve Hanneke
• Shay Moran
• Jonathan Shafer

We present new upper and lower bounds on the number of learner mistakes in the `transductive' online learning setting of Ben-David, Kushilevitz and Mansour (1997). This setting is similar to standard online learning, except that the adversary fixes a sequence of instances $x_1, \dots, x_n$ to be labeled at the start of the game, and this sequence is known to the learner. Qualitatively, we prove a \emph{trichotomy}, stating that the minimal number of mistakes made by the learner as $n$ grows can take only one of precisely three possible values: $n$, $\Theta\left(\log (n)\right)$, or $\Theta(1)$. Furthermore, this behavior is determined by a combination of the VC dimension and the Littlestone dimension. Quantitatively, we show a variety of bounds relating the number of mistakes to well-known combinatorial dimensions. In particular, we improve the known lower bound on the constant in the $\Theta(1)$ case from $\Omega\left(\sqrt{\log(d)}\right)$ to $\Omega(\log(d))$ where $d$ is the Littlestone dimension. Finally, we extend our results to cover multiclass classification and the agnostic setting.

NeurIPS Conference 2023 Conference Paper

Adversarial Resilience in Sequential Prediction via Abstention

• Surbhi Goel
• Steve Hanneke
• Shay Moran
• Abhishek Shetty

We study the problem of sequential prediction in the stochastic setting with an adversary that is allowed to inject clean-label adversarial (or out-of-distribution) examples. Algorithms designed to handle purely stochastic data tend to fail in the presence of such adversarial examples, often leading to erroneous predictions. This is undesirable in many high-stakes applications such as medical recommendations, where abstaining from predictions on adversarial examples is preferable to misclassification. On the other hand, assuming fully adversarial data leads to very pessimistic bounds that are often vacuous in practice. To move away from these pessimistic guarantees, we propose a new model of sequential prediction that sits between the purely stochastic and fully adversarial settings by allowing the learner to abstain from making a prediction at no cost on adversarial examples, thereby asking the learner to make predictions with certainty. Assuming access to the marginal distribution on the non-adversarial examples, we design a learner whose error scales with the VC dimension (mirroring the stochastic setting) of the hypothesis class, as opposed to the Littlestone dimension which characterizes the fully adversarial setting. Furthermore, we design learners for VC dimension~1 classes and the class of axis-aligned rectangles, which work even in the absence of access to the marginal distribution. Our key technical contribution is a novel measure for quantifying uncertainty for learning VC classes, which may be of independent interest.

NeurIPS Conference 2023 Conference Paper

Black-Box Differential Privacy for Interactive ML

• Haim Kaplan
• Yishay Mansour
• Shay Moran
• Kobbi Nissim
• Uri Stemmer

In this work we revisit an interactive variant of joint differential privacy, recently introduced by Naor et al. [2023], and generalize it towards handling online processes in which existing privacy definitions seem too restrictive. We study basic properties of this definition and demonstrate that it satisfies (suitable variants) of group privacy, composition, and post processing. In order to demonstrate the advantages of this privacy definition compared to traditional forms of differential privacy, we consider the basic setting of online classification. We show that any (possibly non-private) learning rule can be effectively transformed to a private learning rule with only a polynomial overhead in the mistake bound. This demonstrates a stark difference with traditional forms of differential privacy, such as the one studied by Golowich and Livni [2021], where only a double exponential overhead in the mistake bound is known (via an information theoretic upper bound).

NeurIPS Conference 2023 Conference Paper

Multiclass Boosting: Simple and Intuitive Weak Learning Criteria

• Nataly Brukhim
• Amit Daniely
• Yishay Mansour
• Shay Moran

We study a generalization of boosting to the multiclass setting. We introduce a weak learning condition for multiclass classification that captures the original notion of weak learnability as being “slightly better than random guessing”. We give a simple and efficient boosting algorithm, that does not require realizability assumptions and its sample and oracle complexity bounds are independent of the number of classes. In addition, we utilize our new boosting technique in several theoretical applications within the context of List PAC Learning. First, we establish an equivalence to weak PAC learning. Furthermore, we present a new result on boosting for list learners, as well as provide a novel proof for the characterization of multiclass PAC learning and List PAC learning. Notably, our technique gives rise to simplified algorithms and analysis compared to previous works.

FOCS Conference 2023 Conference Paper

Stability and Replicability in Learning

• Zachary Chase 0001
• Shay Moran
• Amir Yehudayoff

Replicability is essential in science as it allows us to validate and verify research findings. Impagliazzo, Lei, Pitassi and Sorrell ('22) recently initiated the study of replicability in machine learning. A learning algorithm is replicable if it typically produces the same output when applied on two i. i. d. inputs using the same internal randomness. We study a variant of replicability that does not involve fixing the randomness. An algorithm satisfies this form of replicability if it typically produces the same output when applied on two i. i. d. inputs (without fixing the internal randomness). This variant is called global stability and was introduced by Bun, Livni and Moran ('20) in the context of differential privacy. Impagliazzo et al. showed how to boost any replicable algorithm so that it produces the same output with probability arbitrarily close to 1. In contrast, we demonstrate that for numerous learning tasks, global stability can only be accomplished weakly, where the same output is produced only with probability bounded away from 1. To overcome this limitation, we introduce the concept of list replicability, which is equivalent to global stability. Moreover, we prove that list replicability can be boosted so that it is achieved with probability arbitrarily close to 1. We also describe basic relations between standard learningtheoretic complexity measures and list replicable numbers. Our results, in addition, imply that besides trivial cases, replicable algorithms (in the sense of Impagliazzo et al.) must be randomized. The proof of the impossibility result is based on a topological fixed-point theorem. For every algorithm, we are able to locate a "hard input distribution by applying the Poincaré-Miranda theorem in a related topological setting. The equivalence between global stability and list replicability is algorithmic.

ICML Conference 2023 Conference Paper

Statistical Indistinguishability of Learning Algorithms

• Alkis Kalavasis
• Amin Karbasi
• Shay Moran
• Grigoris Velegkas

When two different parties use the same learning rule on their own data, how can we test whether the distributions of the two outcomes are similar? In this paper, we study the similarity of outcomes of learning rules through the lens of the Total Variation (TV) distance of distributions. We say that a learning rule is TV indistinguishable if the expected TV distance between the posterior distributions of its outputs, executed on two training data sets drawn independently from the same distribution, is small. We first investigate the learnability of hypothesis classes using TV indistinguishable learners. Our main results are information-theoretic equivalences between TV indistinguishability and existing algorithmic stability notions such as replicability and approximate differential privacy. Then, we provide statistical amplification and boosting algorithms for TV indistinguishable learners.

NeurIPS Conference 2023 Conference Paper

The Bayesian Stability Zoo

• Shay Moran
• Hilla Schefler
• Jonathan Shafer

We show that many definitions of stability found in the learning theory literature are equivalent to one another. We distinguish between two families of definitions of stability: distribution-dependent and distribution-independent Bayesian stability. Within each family, we establish equivalences between various definitions, encompassing approximate differential privacy, pure differential privacy, replicability, global stability, perfect generalization, TV stability, mutual information stability, KL-divergence stability, and Rényi-divergence stability. Along the way, we prove boosting results that enable the amplification of the stability of a learning rule. This work is a step towards a more systematic taxonomy of stability notions in learning theory, which can promote clarity and an improved understanding of an array of stability concepts that have emerged in recent years.

FOCS Conference 2022 Conference Paper

A Characterization of Multiclass Learnability

• Nataly Brukhim
• Daniel Carmon
• Irit Dinur
• Shay Moran
• Amir Yehudayoff

A seminal result in learning theory characterizes the PAC learnability of binary classes through the Vapnik-Chervonenkis dimension. Extending this characterization to the general multiclass setting has been open since the pioneering works on multiclass PAC learning in the late 1980s. This work resolves this problem: we characterize multiclass PAC learnability through the DS dimension, a combinatorial dimension defined by Daniely and Shalev-Shwartz, (2014). The classical characterization of the binary case boils down to empirical risk minimization. In contrast, our characterization of the multiclass case involves a variety of algorithmic ideas; these include a natural setting we call list PAC learning. In the list learning setting, instead of predicting a single outcome for a given unseen input, the goal is to provide a short menu of predictions. Our second main result concerns the Natarajan dimension, which has been a central candidate for characterizing multiclass learnability. This dimension was introduced by Natarajan (1988) as a barrier for PAC learning. He furthered showed that it is the only barrier, provided that the number of labels is bounded. Whether the Natarajan dimension characterizes PAC learnability in general has been posed as an open question in several papers since. This work provides a negative answer: we construct a non-learnable class with Natarajan dimension 1. For the construction, we identify a fundamental connection between concept classes and topology (i. e. , colorful simplicial complexes). We crucially rely on a deep and involved construction of hyperbolic pseudo-manifolds by Januszkiewicz and Światkowski. It is interesting that hyperbolicity is directly related to learning problems that are difficult to solve although no obvious barriers exist. This is another demonstration of the fruitful links machine learning has with different areas in mathematics.

ICML Conference 2022 Conference Paper

A Resilient Distributed Boosting Algorithm

• Yuval Filmus
• Idan Mehalel
• Shay Moran

Given a learning task where the data is distributed among several parties, communication is one of the fundamental resources which the parties would like to minimize. We present a distributed boosting algorithm which is resilient to a limited amount of noise. Our algorithm is similar to classical boosting algorithms, although it is equipped with a new component, inspired by Impagliazzo’s hard-core lemma (Impagliazzo, 1995), adding a robustness quality to the algorithm. We also complement this result by showing that resilience to any asymptotically larger noise is not achievable by a communication-efficient algorithm.

UAI Conference 2022 Conference Paper

Active learning with label comparisons

• Gal Yona
• Shay Moran
• Gal Elidan
• Amir Globerson

Supervised learning typically relies on manual annotation of the true labels. When there are many potential classes, searching for the best one can be prohibitive for a human annotator. On the other hand, comparing two candidate labels is often much easier. We focus on this type of pairwise supervision and ask how it can be used effectively in learning, and in particular in active learning. We obtain several insightful results in this context. In principle, finding the best of k labels can be done with k-1 active queries. We show that there is a natural class where this approach is sub-optimal, and that there is a more comparison-efficient active learning scheme. A key element in our analysis is the “label neighborhood graph” of the true distribution, which has an edge between two classes if they share a decision boundary. We also show that in the PAC setting, pairwise comparisons cannot provide improved sample complexity in the worst case. We complement our theoretical results with experiments, clearly demonstrating the effect of the neighborhood graph on sample complexity.

NeurIPS Conference 2022 Conference Paper

Integral Probability Metrics PAC-Bayes Bounds

• Ron Amit
• Baruch Epstein
• Shay Moran
• Ron Meir

We present a PAC-Bayes-style generalization bound which enables the replacement of the KL-divergence with a variety of Integral Probability Metrics (IPM). We provide instances of this bound with the IPM being the total variation metric and the Wasserstein distance. A notable feature of the obtained bounds is that they naturally interpolate between classical uniform convergence bounds in the worst case (when the prior and posterior are far away from each other), and improved bounds in favorable cases (when the posterior and prior are close). This illustrates the possibility of reinforcing classical generalization bounds with algorithm- and data-dependent components, thus making them more suitable to analyze algorithms that use a large hypothesis space.

NeurIPS Conference 2022 Conference Paper

On Optimal Learning Under Targeted Data Poisoning

• Steve Hanneke
• Amin Karbasi
• Mohammad Mahmoody
• Idan Mehalel
• Shay Moran

Consider the task of learning a hypothesis class $\mathcal{H}$ in the presence of an adversary that can replace up to an $\eta$ fraction of the examples in the training set with arbitrary adversarial examples. The adversary aims to fail the learner on a particular target test point $x$ which is \emph{known} to the adversary but not to the learner. In this work we aim to characterize the smallest achievable error $\epsilon=\epsilon(\eta)$ by the learner in the presence of such an adversary in both realizable and agnostic settings. We fully achieve this in the realizable setting, proving that $\epsilon=\Theta(\mathtt{VC}(\mathcal{H})\cdot \eta)$, where $\mathtt{VC}(\mathcal{H})$ is the VC dimension of $\mathcal{H}$. Remarkably, we show that the upper bound can be attained by a deterministic learner. In the agnostic setting we reveal a more elaborate landscape: we devise a deterministic learner with a multiplicative regret guarantee of $\epsilon \leq C\cdot\mathtt{OPT} + O(\mathtt{VC}(\mathcal{H})\cdot \eta)$, where $C > 1$ is a universal numerical constant. We complement this by showing that for any deterministic learner there is an attack which worsens its error to at least $2\cdot \mathtt{OPT}$. This implies that a multiplicative deterioration in the regret is unavoidable in this case. Finally, the algorithms we develop for achieving the optimal rates are inherently improper. Nevertheless, we show that for a variety of natural concept classes, such as linear classifiers, it is possible to retain the dependence $\epsilon=\Theta_{\mathcal{H}}(\eta)$ by a proper algorithm in the realizable setting. Here $\Theta_{\mathcal{H}}$ conceals a polynomial dependence on $\mathtt{VC}(\mathcal{H})$.

NeurIPS Conference 2022 Conference Paper

Universal Rates for Interactive Learning

• Steve Hanneke
• Amin Karbasi
• Shay Moran
• Grigoris Velegkas

Consider the task of learning an unknown concept from a given concept class; to what extent does interacting with a domain expert accelerate the learning process? It is common to measure the effectiveness of learning algorithms by plotting the "learning curve", that is, the decay of the error rate as a function of the algorithm's resources (examples, queries, etc). Thus, the overarching question in this work is whether (and which kind of) interaction accelerates the learning curve. Previous work in interactive learning focused on uniform bounds on the learning rates which only capture the upper envelope of the learning curves over families of data distributions. We thus formalize our overarching question within the distribution dependent framework of universal learning, which aims to understand the performance of learning algorithms on every data distribution, but without requiring a single upper bound which applies uniformly to all distributions. Our main result reveals a fundamental trichotomy of interactive learning rates, thus providing a complete characterization of universal interactive learning. As a corollary we deduce a strong affirmative answer to our overarching question, showing that interaction is beneficial. Remarkably, we show that in important cases such benefits are realized with label queries, that is, by active learning algorithms. On the other hand, our lower bounds apply to arbitrary binary queries and, hence, they hold in any interactive learning setting.

FOCS Conference 2021 Conference Paper

A Theory of PAC Learnability of Partial Concept Classes

• Noga Alon
• Steve Hanneke
• Ron Holzman
• Shay Moran

We extend the classical theory of PAC learning in a way which allows to model a rich variety of practical learning tasks where the data satisfy special properties that ease the learning process. For example, tasks where the distance of the data from the decision boundary is bounded away from zero, or tasks where the data lie on a lower dimensional surface. The basic and simple idea is to consider partial concepts: these are functions that can be undefined on certain parts of the space. When learning a partial concept, we assume that the source distribution is supported only on points where the partial concept is defined. This way, one can naturally express assumptions on the data such as lying on a lower dimensional surface, or that it satisfies margin conditions. In contrast, it is not at all clear that such assumptions can be expressed by the traditional PAC theory using learnable total concept classes, and in fact we exhibit easy-to-learn partial concept classes which provably cannot be captured by the traditional PAC theory. This also resolves, in a strong negative sense, a question posed by Attias, Kontorovich, and Mansour (2019). We characterize PAC learnability of partial concept classes and reveal an algorithmic landscape which is fundamentally different than the classical one. For example, in the classical PAC model, learning boils down to Empirical Risk Minimization (ERM). This basic principle follows from Uniform Convergence and the Fundamental Theorem of PAC Learning (Vapnik and Chervonenkis, 1971, 1974b; Blumer, Ehrenfeucht, Haussler, and Warmuth, 1989; Hodges, 1993). In stark contrast, we show that the ERM principle fails spectacularly in explaining learnability of partial concept classes. In fact, we demonstrate classes that are incredibly easy to learn, but such that any algorithm that learns them must use an hypothesis space with unbounded VC dimension. We also find that the sample compression conjecture of Littlestone and Warmuth fails in this setting. Our impossibility results hinge on the recent breakthroughs in communication complexity and graph theory by Göös (2015); Ben-David, Hatami, and Tal (2017); Balodis, Ben-David, Göös, Jain, and Kothari (2021). Thus, this theory features problems that cannot be represented in the traditional way and cannot be solved in the traditional way. We view this as evidence that it might provide insights on the nature of learnability in realistic scenarios which the classical theory fails to explain. We include in the paper suggestions for future research and open problems in several contexts, including combinatorics, geometry, and learning theory.

STOC Conference 2021 Conference Paper

A theory of universal learning

• Olivier Bousquet
• Steve Hanneke
• Shay Moran
• Ramon van Handel
• Amir Yehudayoff

How quickly can a given class of concepts be learned from examples? It is common to measure the performance of a supervised machine learning algorithm by plotting its “learning curve”, that is, the decay of the error rate as a function of the number of training examples. However, the classical theoretical framework for understanding learnability, the PAC model of Vapnik-Chervonenkis and Valiant, does not explain the behavior of learning curves: the distribution-free PAC model of learning can only bound the upper envelope of the learning curves over all possible data distributions. This does not match the practice of machine learning, where the data source is typically fixed in any given scenario, while the learner may choose the number of training examples on the basis of factors such as computational resources and desired accuracy. In this paper, we study an alternative learning model that better captures such practical aspects of machine learning, but still gives rise to a complete theory of the learnable in the spirit of the PAC model. More precisely, we consider the problem of universal learning, which aims to understand the performance of learning algorithms on every data distribution, but without requiring uniformity over the distribution. The main result of this paper is a remarkable trichotomy: there are only three possible rates of universal learning. More precisely, we show that the learning curves of any given concept class decay either at an exponential, linear, or arbitrarily slow rates. Moreover, each of these cases is completely characterized by appropriate combinatorial parameters, and we exhibit optimal learning algorithms that achieve the best possible rate in each case. For concreteness, we consider in this paper only the realizable case, though analogous results are expected to extend to more general learning scenarios.

STOC Conference 2021 Conference Paper

Adversarial laws of large numbers and optimal regret in online classification

• Noga Alon
• Omri Ben-Eliezer
• Yuval Dagan
• Shay Moran
• Moni Naor
• Eylon Yogev

Laws of large numbers guarantee that given a large enough sample from some population, the measure of any fixed sub-population is well-estimated by its frequency in the sample. We study laws of large numbers in sampling processes that can affect the environment they are acting upon and interact with it. Specifically, we consider the sequential sampling model proposed by Ben-Eliezer and Yogev (2020), and characterize the classes which admit a uniform law of large numbers in this model: these are exactly the classes that are online learnable . Our characterization may be interpreted as an online analogue to the equivalence between learnability and uniform convergence in statistical (PAC) learning. The sample-complexity bounds we obtain are tight for many parameter regimes, and as an application, we determine the optimal regret bounds in online learning, stated in terms of Littlestone’s dimension , thus resolving the main open question from Ben-David, Pál, and Shalev-Shwartz (2009), which was also posed by Rakhlin, Sridharan, and Tewari (2015).

STOC Conference 2021 Conference Paper

Boosting simple learners

• Noga Alon
• Alon Gonen
• Elad Hazan
• Shay Moran

Boosting is a celebrated machine learning approach which is based on the idea of combining weak and moderately inaccurate hypotheses to a strong and accurate one. We study boosting under the assumption that the weak hypotheses belong to a class of bounded capacity. This assumption is inspired by the common convention that weak hypotheses are “rules-of-thumbs” from an “easy-to-learn class”. (Schapire and Freund ’12, Shalev-Shwartz and Ben-David ’14.) Formally, we assume the class of weak hypotheses has a bounded VC dimension. We focus on two main questions: (i) Oracle Complexity: How many weak hypotheses are needed in order to produce an accurate hypothesis? We design a novel boosting algorithm and demonstrate that it circumvents a classical lower bound by Freund and Schapire (’95, ’12). Whereas the lower bound shows that Ω(1/γ 2 ) weak hypotheses with γ-margin are sometimes necessary, our new method requires only Õ(1/γ) weak hypothesis, provided that they belong to a class of bounded VC dimension. Unlike previous boosting algorithms which aggregate the weak hypotheses by majority votes, the new boosting algorithm uses more complex (“deeper”) aggregation rules. We complement this result by showing that complex aggregation rules are in fact necessary to circumvent the aforementioned lower bound. (ii) Expressivity: Which tasks can be learned by boosting weak hypotheses from a bounded VC class? Can complex concepts that are “far away” from the class be learned? Towards answering the first question we identify a combinatorial-geometric parameter which captures the expressivity of base-classes in boosting. As a corollary we provide an affirmative answer to the second question for many well-studied classes, including half-spaces and decision stumps. Along the way, we establish and exploit connections with Discrepancy Theory.

STOC Conference 2021 Invited Paper

Learnability can be independent of set theory (invited paper)

• Shai Ben-David
• Pavel Hrubes
• Shay Moran
• Amir Shpilka
• Amir Yehudayoff

NeurIPS Conference 2021 Conference Paper

Multiclass Boosting and the Cost of Weak Learning

• Nataly Brukhim
• Elad Hazan
• Shay Moran
• Indraneel Mukherjee
• Robert E. Schapire

Boosting is an algorithmic approach which is based on the idea of combining weak and moderately inaccurate hypotheses to a strong and accurate one. In this work we study multiclass boosting with a possibly large number of classes or categories. Multiclass boosting can be formulated in various ways. Here, we focus on an especially natural formulation in which the weak hypotheses are assumed to belong to an ''easy-to-learn'' base class, and the weak learner is an agnostic PAC learner for that class with respect to the standard classification loss. This is in contrast with other, more complicated losses as have often been considered in the past. The goal of the overall boosting algorithm is then to learn a combination of weak hypotheses by repeatedly calling the weak learner. We study the resources required for boosting, especially how theydepend on the number of classes $k$, for both the booster and weak learner. We find that the boosting algorithm itself only requires $O(\log k)$samples, as we show by analyzing a variant of AdaBoost for oursetting. In stark contrast, assuming typical limits on the number of weak-learner calls, we prove that the number of samples required by a weak learner is at least polynomial in $k$, exponentially more than thenumber of samples needed by the booster. Alternatively, we prove that the weak learner's accuracy parametermust be smaller than an inverse polynomial in $k$, showing that the returned weakhypotheses must be nearly the best in their class when $k$ is large. We also prove a trade-off between number of oracle calls and theresources required of the weak learner, meaning that the fewer calls to theweak learner the more that is demanded on each call.

FOCS Conference 2021 Conference Paper

Statistically Near-Optimal Hypothesis Selection

• Olivier Bousquet
• Mark Braverman
• Gillat Kol
• Klim Efremenko
• Shay Moran

Hypothesis Selection is a fundamental distribution learning problem where given a comparator-class $\mathcal{Q}=\{q_{1}, \ldots, q_{n}\}$ of distributions, and a sampling access to an unknown target distribution $p$, the goal is to output a distribution $q$ such that $\mathsf{TV}(p, q)$ is close to opt, where $\mathsf{opt}=\min\nolimits_{i}\{\mathsf{TV}(p, q_{i})\}$ and TV (. ,.) denotes the total-variation distance. Despite the fact that this problem has been studied since the 19th century, its complexity in terms of basic resources, such as number of samples and approximation guarantees, remains unsettled (this is discussed, e. g. , in the charming book by Devroye and Lugosi '00). This is in stark contrast with other (younger) learning settings, such as PAC learning, for which these complexities are well understood. We derive an optimal 2-approximation learning strategy for the Hypothesis Selection problem, outputting $q$ such that, $\mathsf{TV}(p, q)\leq 2\cdot\text{opt}+\varepsilon$, with a (nearly) optimal sample complexity of $\tilde{O}(\log n/\varepsilon^{2})$. This is the first algorithm that simultaneously achieves the best approximation factor and sample complexity: previously, Bousquet, Kane, and Moran (COLT ‘19) gave a learner achieving the optimal 2-approximation, but with an exponentially worse sample complexity of $\tilde{O}(\sqrt{n}/\varepsilon^{2. 5})$, and Yatracos (Annals of Statistics '85) gave a learner with optimal sample complexity of $O(\log n/\varepsilon^{2})$ but with a sub-optimal approximation factor of 3. We mention that many works in the Density Estimation (a. k. a. , Distribution Learning) literature use Hypothesis Selection as a black box subroutine. Our result therefore implies an improvement on the approximation factors obtained by these works, while keeping their sample complexity intact. For example, our result improves the approximation factor of the algorithm of Ashtiani, Ben-David, Harvey, Liaw, and Mehrabian (JACM '20) for agnostic learning of mixtures of gaussians from 9 to 6, while maintaining its nearly-tight sample complexity.

NeurIPS Conference 2021 Conference Paper

Towards a Unified Information-Theoretic Framework for Generalization

• Mahdi Haghifam
• Gintare Karolina Dziugaite
• Shay Moran
• Dan Roy

In this work, we investigate the expressiveness of the "conditional mutual information" (CMI) framework of Steinke and Zakynthinou (2020) and the prospect of using it to provide a unified framework for proving generalization bounds in the realizable setting. We first demonstrate that one can use this framework to express non-trivial (but sub-optimal) bounds for any learning algorithm that outputs hypotheses from a class of bounded VC dimension. We then explore two directions of strengthening this bound: (i) Can the CMI framework express optimal bounds for VC classes? (ii) Can the CMI framework be used to analyze algorithms whose output hypothesis space is unrestricted (i. e. has an unbounded VC dimension)? With respect to Item (i) we prove that the CMI framework yields the optimal bound on the expected risk of Support Vector Machines (SVMs) for learning halfspaces. This result is an application of our general result showing that stable compression schemes Bousquet al. (2020) of size $k$ have uniformly bounded CMI of order $O(k)$. We further show that an inherent limitation of proper learning of VC classes contradicts the existence of a proper learner with constant CMI, and it implies a negative resolution to an open problem of Steinke and Zakynthinou (2020). We further study the CMI of empirical risk minimizers (ERMs) of class $H$ and show that it is possible to output all consistent classifiers (version space) with bounded CMI if and only if $H$ has a bounded star number (Hanneke and Yang (2015)). With respect to Item (ii) we prove a general reduction showing that "leave-one-out" analysis is expressible via the CMI framework. As a corollary we investigate the CMI of the one-inclusion-graph algorithm proposed by Haussler et al. (1994). More generally, we show that the CMI framework is universal in the sense that for every consistent algorithm and data distribution, the expected risk vanishes as the number of samples diverges if and only if its evaluated CMI has sublinear growth with the number of samples.

NeurIPS Conference 2020 Conference Paper

A Limitation of the PAC-Bayes Framework

• Roi Livni
• Shay Moran

PAC-Bayes is a useful framework for deriving generalization bounds which was introduced by McAllester ('98). This framework has the flexibility of deriving distribution- and algorithm-dependent bounds, which are often tighter than VC-related uniform convergence bounds. In this manuscript we present a limitation for the PAC-Bayes framework. We demonstrate an easy learning task which is not amenable to a PAC-Bayes analysis. Specifically, we consider the task of linear classification in 1D; it is well-known that this task is learnable using just $O(\log(1/\delta)/\epsilon)$ examples. On the other hand, we show that this fact can not be proved using a PAC-Bayes analysis: for any algorithm that learns 1-dimensional linear classifiers there exists a (realizable) distribution for which the PAC-Bayes bound is arbitrarily large.

FOCS Conference 2020 Conference Paper

An Equivalence Between Private Classification and Online Prediction

• Mark Bun
• Roi Livni
• Shay Moran

We prove that every concept class with finite Littlestone dimension can be learned by an (approximate) differentially-private algorithm. This answers an open question of Alon et al. (STOC 2019) who proved the converse statement (this question was also asked by Neel et al. (FOCS 2019)). Together these two results yield an equivalence between online learnability and private PAC learnability. We introduce a new notion of algorithmic stability called “global stability” which is essential to our proof and may be of independent interest. We also discuss an application of our results to boosting the privacy and accuracy parameters of differentially-private learners.

NeurIPS Conference 2020 Conference Paper

Learning from Mixtures of Private and Public Populations

• Raef Bassily
• Shay Moran
• Anupama Nandi

We initiate the study of a new model of supervised learning under privacy constraints. Imagine a medical study where a dataset is sampled from a population of both healthy and unhealthy individuals. Suppose healthy individuals have no privacy concerns (in such case, we call their data ``public'') while the unhealthy individuals desire stringent privacy protection for their data. In this example, the population (data distribution) is a mixture of private (unhealthy) and public (healthy) sub-populations that could be very different. Inspired by the above example, we consider a model in which the population $\cD$ is a mixture of two possibly distinct sub-populations: a private sub-population $\Dprv$ of private and sensitive data, and a public sub-population $\Dpub$ of data with no privacy concerns. Each example drawn from $\cD$ is assumed to contain a privacy-status bit that indicates whether the example is private or public. The goal is to design a learning algorithm that satisfies differential privacy only with respect to the private examples. Prior works in this context assumed a homogeneous population where private and public data arise from the same distribution, and in particular designed solutions which exploit this assumption. We demonstrate how to circumvent this assumption by considering, as a case study, the problem of learning linear classifiers in $R^d$. We show that in the case where the privacy status is correlated with the target label (as in the above example), linear classifiers in $R^d$ can be learned, in the agnostic as well as the realizable setting, with sample complexity which is comparable to that of the classical (non-private) PAC-learning. It is known that this task is impossible if all the data is considered private.

NeurIPS Conference 2020 Conference Paper

Online Agnostic Boosting via Regret Minimization

• Nataly Brukhim
• Xinyi Chen
• Elad Hazan
• Shay Moran

Boosting is a widely used machine learning approach based on the idea of aggregating weak learning rules. While in statistical learning numerous boosting methods exist both in the realizable and agnostic settings, in online learning they exist only in the realizable case. In this work we provide the first agnostic online boosting algorithm; that is, given a weak learner with only marginally-better-than-trivial regret guarantees, our algorithm boosts it to a strong learner with sublinear regret. Our algorithm is based on an abstract (and simple) reduction to online convex optimization, which efficiently converts an arbitrary online convex optimizer to an online booster. Moreover, this reduction extends to the statistical as well as the online realizable settings, thus unifying the 4 cases of statistical/online and agnostic/realizable boosting.

ICML Conference 2020 Conference Paper

Private Query Release Assisted by Public Data

• Raef Bassily
• Albert Cheu
• Shay Moran
• Aleksandar Nikolov
• Jonathan R. Ullman
• Zhiwei Steven Wu

We study the problem of differentially private query release assisted by access to public data. In this problem, the goal is to answer a large class $\mathcal{H}$ of statistical queries with error no more than $\alpha$ using a combination of public and private samples. The algorithm is required to satisfy differential privacy only with respect to the private samples. We study the limits of this task in terms of the private and public sample complexities. Our upper and lower bounds on the private sample complexity have matching dependence on the dual VC-dimension of $\mathcal{H}$. For a large category of query classes, our bounds on the public sample complexity have matching dependence on $\alpha$.

NeurIPS Conference 2020 Conference Paper

Synthetic Data Generators -- Sequential and Private

• Olivier Bousquet
• Roi Livni
• Shay Moran

We study the sample complexity of private synthetic data generation over an unbounded sized class of statistical queries, and show that any class that is privately proper PAC learnable admits a private synthetic data generator (perhaps non-efficient). A differentially private synthetic generator is an algorithm that receives an IID data and publishes synthetic data that is indistinguishable from the true data w. r. t a given fixed class of statistical queries. The synthetic data set can then be used by a data scientist without compromising the privacy of the original data set. Previous work on synthetic data generators focused on the case that the query class $\D$ is finite and obtained sample complexity bounds that scale logarithmically with the size $|\D|$. Here we construct a private synthetic data generator whose sample complexity is independent of the domain size, and we replace finiteness with the assumption that $\D$ is privately PAC learnable (a formally weaker task, hence we obtain equivalence between the two tasks). Our proof relies on a new type of synthetic data generator, Sequential Synthetic Data Generators, which we believe may be of interest of their own right. A sequential SDG is defined by a sequential game between a generator that proposes synthetic distributions and a discriminator that tries to distinguish between real and fake distributions. We characterize the classes that admit a sequential-SDG and show that they are exactly Littlestone classes. Given the online nature of the sequential setting, it is natural that Littlestone classes arise in this context. Nevertheless, the characterization of sequential--SDGs by Littlestone classes turns out to be technically challenging, and to the best of the author's knowledge, does not follow via simple reductions to online prediction.

NeurIPS Conference 2019 Conference Paper

An adaptive nearest neighbor rule for classification

• Akshay Balsubramani
• Sanjoy Dasgupta
• Yoav Freund
• Shay Moran

We introduce a variant of the $k$-nearest neighbor classifier in which $k$ is chosen adaptively for each query, rather than supplied as a parameter. The choice of $k$ depends on properties of each neighborhood, and therefore may significantly vary between different points. (For example, the algorithm will use larger $k$ for predicting the labels of points in noisy regions. ) We provide theory and experiments that demonstrate that the algorithm performs comparably to, and sometimes better than, $k$-NN with an optimal choice of $k$. In particular, we derive bounds on the convergence rates of our classifier that depend on a local quantity we call the ``advantage'' which is significantly weaker than the Lipschitz conditions used in previous convergence rate proofs. These generalization bounds hinge on a variant of the seminal Uniform Convergence Theorem due to Vapnik and Chervonenkis; this variant concerns conditional probabilities and may be of independent interest.

NeurIPS Conference 2019 Conference Paper

Learning to Screen

• Alon Cohen
• Avinatan Hassidim
• Haim Kaplan
• Yishay Mansour
• Shay Moran

Imagine a large firm with multiple departments that plans a large recruitment. Candidates arrive one-by-one, and for each candidate the firm decides, based on her data (CV, skills, experience, etc), whether to summon her for an interview. The firm wants to recruit the best candidates while minimizing the number of interviews. We model such scenarios as an assignment problem between items (candidates) and categories (departments): the items arrive one-by-one in an online manner, and upon processing each item the algorithm decides, based on its value and the categories it can be matched with, whether to retain or discard it (this decision is irrevocable). The goal is to retain as few items as possible while guaranteeing that the set of retained items contains an optimal matching. We consider two variants of this problem: (i) in the first variant it is assumed that the $n$ items are drawn independently from an unknown distribution $D$. (ii) In the second variant it is assumed that before the process starts, the algorithm has an access to a training set of $n$ items drawn independently from the same unknown distribution (e. g. \ data of candidates from previous recruitment seasons). We give tight bounds on the minimum possible number of retained items in each of these variants. These results demonstrate that one can retain exponentially less items in the second variant (with the training set). Our algorithms and analysis utilize ideas and techniques from statistical learning theory and from discrete algorithms.

NeurIPS Conference 2019 Conference Paper

Limits of Private Learning with Access to Public Data

• Noga Alon
• Raef Bassily
• Shay Moran

We consider learning problems where the training set consists of two types of examples: private and public. The goal is to design a learning algorithm that satisfies differential privacy only with respect to the private examples. This setting interpolates between private learning (where all examples are private) and classical learning (where all examples are public). We study the limits of learning in this setting in terms of private and public sample complexities. We show that any hypothesis class of VC-dimension $d$ can be agnostically learned up to an excess error of $\alpha$ using only (roughly) $d/\alpha$ public examples and $d/\alpha^2$ private labeled examples. This result holds even when the public examples are unlabeled. This gives a quadratic improvement over the standard $d/\alpha^2$ upper bound on the public sample complexity (where private examples can be ignored altogether if the public examples are labeled). Furthermore, we give a nearly matching lower bound, which we prove via a generic reduction from this setting to the one of private learning without public data.

NeurIPS Conference 2019 Conference Paper

Private Learning Implies Online Learning: An Efficient Reduction

• Alon Gonen
• Elad Hazan
• Shay Moran

We study the relationship between the notions of differentially private learning and online learning. Several recent works have shown that differentially private learning implies online learning, but an open problem of Neel, Roth, and Wu \cite{NeelAaronRoth2018} asks whether this implication is {\it efficient}. Specifically, does an efficient differentially private learner imply an efficient online learner? In this paper we resolve this open question in the context of pure differential privacy. We derive an efficient black-box reduction from differentially private learning to online learning from expert advice.

STOC Conference 2019 Conference Paper

Private PAC learning implies finite Littlestone dimension

• Noga Alon
• Roi Livni
• Maryanthe Malliaris
• Shay Moran

We show that every approximately differentially private learning algorithm (possibly improper) for a class H with Littlestone dimension d requires Ω(log * ( d )) examples. As a corollary it follows that the class of thresholds over ℕ can not be learned in a private manner; this resolves open questions due to [Bun et al. 2015] and [Feldman and Xiao, 2015]. We leave as an open question whether every class with a finite Littlestone dimension can be learned by an approximately differentially private algorithm.

STOC Conference 2018 Conference Paper

Near-optimal linear decision trees for k-SUM and related problems

• Daniel M. Kane
• Shachar Lovett
• Shay Moran

We construct near optimal linear decision trees for a variety of decision problems in combinatorics and discrete geometry. For example, for any constant k , we construct linear decision trees that solve the k -SUM problem on n elements using O ( n log 2 n ) linear queries. Moreover, the queries we use are comparison queries, which compare the sums of two k -subsets; when viewed as linear queries, comparison queries are 2 k -sparse and have only {−1,0,1} coefficients. We give similar constructions for sorting sumsets A + B and for solving the SUBSET-SUM problem, both with optimal number of queries, up to poly-logarithmic terms. Our constructions are based on the notion of “inference dimension”, recently introduced by the authors in the context of active classification with comparison queries. This can be viewed as another contribution to the fruitful link between machine learning and discrete geometry, which goes back to the discovery of the VC dimension.

FOCS Conference 2017 Conference Paper

Active Classification with Comparison Queries

• Daniel M. Kane
• Shachar Lovett
• Shay Moran
• Jiapeng Zhang

We study an extension of active learning in which the learning algorithm may ask the annotator to compare the distances of two examples from the boundary of their label-class. For example, in a recommendation system application (say for restaurants), the annotator may be asked whether she liked or disliked a specific restaurant (a label query); or which one of two restaurants did she like more (a comparison query). We focus on the class of half spaces, and show that under natural assumptions, such as large margin or bounded bit-description of the input examples, it is possible to reveal all the labels of a sample of size n using approximately O(log n) queries. This implies an exponential improvement over classical active learning, where only label queries are allowed. We complement these results by showing that if any of these assumptions is removed then, in the worst case, Ω(n) queries are required. Our results follow from a new general framework of active learning with additional queries. We identify a combinatorial dimension, called the inference dimension, that captures the query complexity when each additional query is determined by O(1) examples (such as comparison queries, each of which is determined by the two compared examples). Our results for half spaces follow by bounding the inference dimension in the cases discussed above.

NeurIPS Conference 2017 Conference Paper

Submultiplicative Glivenko-Cantelli and Uniform Convergence of Revenues

• Noga Alon
• Moshe Babaioff
• Yannai A. Gonczarowski
• Yishay Mansour
• Shay Moran
• Amir Yehudayoff

In this work we derive a variant of the classic Glivenko-Cantelli Theorem, which asserts uniform convergence of the empirical Cumulative Distribution Function (CDF) to the CDF of the underlying distribution. Our variant allows for tighter convergence bounds for extreme values of the CDF. We apply our bound in the context of revenue learning, which is a well-studied problem in economics and algorithmic game theory. We derive sample-complexity bounds on the uniform convergence rate of the empirical revenues to the true revenues, assuming a bound on the k'th moment of the valuations, for any (possibly fractional) k > 1. For uniform convergence in the limit, we give a complete characterization and a zero-one law: if the first moment of the valuations is finite, then uniform convergence almost surely occurs; conversely, if the first moment is infinite, then uniform convergence almost never occurs.

STOC Conference 2017 Conference Paper

Twenty (simple) questions

• Yuval Dagan
• Yuval Filmus
• Ariel Gabizon
• Shay Moran

MFCS Conference 2016 Conference Paper

Shattered Sets and the Hilbert Function

• Shay Moran
• Cyrus Rashtchian

We study complexity measures on subsets of the boolean hypercube and exhibit connections between algebra (the Hilbert function) and combinatorics (VC theory). These connections yield results in both directions. Our main complexity-theoretic result demonstrates that a large and natural family of linear program feasibility problems cannot be computed by polynomial-sized constant-depth circuits. Moreover, our result applies to a stronger regime in which the hyperplanes are fixed and only the directions of the inequalities are given as input to the circuit. We derive this result by proving that a rich class of extremal functions in VC theory cannot be approximated by low-degree polynomials. We also present applications of algebra to combinatorics. We provide a new algebraic proof of the Sandwich Theorem, which is a generalization of the well-known Sauer-Perles-Shelah Lemma. Finally, we prove a structural result about downward-closed sets, related to the Chvatal conjecture in extremal combinatorics.

NeurIPS Conference 2016 Conference Paper

Supervised learning through the lens of compression

• Ofir David
• Shay Moran
• Amir Yehudayoff

This work continues the study of the relationship between sample compression schemes and statistical learning, which has been mostly investigated within the framework of binary classification. We first extend the investigation to multiclass categorization: we prove that in this case learnability is equivalent to compression of logarithmic sample size and that the uniform convergence property implies compression of constant size. We use the compressibility-learnability equivalence to show that (i) for multiclass categorization, PAC and agnostic PAC learnability are equivalent, and (ii) to derive a compactness theorem for learnability. We then consider supervised learning under general loss functions: we show that in this case, in order to maintain the compressibility-learnability equivalence, it is necessary to consider an approximate variant of compression. We use it to show that PAC and agnostic PAC are not equivalent, even when the loss function has only three values.

FOCS Conference 2015 Conference Paper

Compressing and Teaching for Low VC-Dimension

• Shay Moran
• Amir Shpilka
• Avi Wigderson
• Amir Yehudayoff

In this work we study the quantitative relation between VC-dimension and two other basic parameters related to learning and teaching. Namely, the quality of sample compression schemes and of teaching sets for classes of low VC-dimension. Let C be a binary concept class of size m and VC-dimension d. Prior to this work, the best known upper bounds for both parameters were log(m), while the best lower bounds are linear in d. We present significantly better upper bounds on both as follows. We construct sample compression schemes of size exp(d) for C. This resolves a question of Littlest one and Warmuth (1986). Roughly speaking, we show that given an arbitrary set of labeled examples from an unknown concept in C, one can retain only a subset of exp(d) of them, in a way that allows to recover the labels of all other examples in the set, using additional exp(d) information bits. We further show that there always exists a concept c in C with a teaching set (i. e. A list of c-labeled examples uniquely identifying c in C) of size exp(d) log log(m). This problem was studied by Kuhlmann (1999). Our construction also implies that the recursive teaching (RT) dimension of C is at most exp(d) log log(m) as well. The RT-dimension was suggested by Zilles et al. And Doliwa et al. (2010). The same notion (under the name partial-ID width) was independently studied by Wigderson and Yehuday off (2013). An upper bound on this parameter that depends only on d is known just for the very simple case d=1, and is open even for d=2. We also make small progress towards this seemingly modest goal.