Francesco Orabona

ICML Conference 2025 Conference Paper

A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO

• Xingyu Zhou 0001
• Yulian Wu
• Francesco Orabona

In this paper, we theoretically investigate the effects of noisy labels in offline alignment, with a focus on the interplay between privacy and robustness against adversarial corruption. Specifically, under linear modeling assumptions, we present a unified analysis covering both reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) under different privacy-corruption scenarios, such as Local differential privacy-then-Corruption (LTC), where human preference labels are privatized before being corrupted by an adversary, and Corruption-then-Local differential privacy (CTL), where labels are corrupted before privacy protection. Our analysis leverages a reduction framework that reduces the offline alignment problem under linear modeling assumptions to parameter estimation in logistic regression. This framework allows us to establish an interesting separation result between LTC and CTL, demonstrating that LTC presents a greater challenge than CTL in offline alignment, even under linear models. As important by-products, our findings also advance the state-of-the-art theoretical results in offline alignment under privacy-only or corruption-only scenarios.

ICML Conference 2025 Conference Paper

ATA: Adaptive Task Allocation for Efficient Resource Management in Distributed Machine Learning

• Arto Maranjyan
• El Mehdi Saad
• Peter Richtárik
• Francesco Orabona

Asynchronous methods are fundamental for parallelizing computations in distributed machine learning. They aim to accelerate training by fully utilizing all available resources. However, their greedy approach can lead to inefficiencies using more computation than required, especially when computation times vary across devices. If the computation times were known in advance, training could be fast and resource-efficient by assigning more tasks to faster workers. The challenge lies in achieving this optimal allocation without prior knowledge of the computation time distributions. In this paper, we propose ATA (Adaptive Task Allocation), a method that adapts to heterogeneous and random distributions of worker computation times. Through rigorous theoretical analysis, we show that ATA identifies the optimal task allocation and performs comparably to methods with prior knowledge of computation times. Experimental results further demonstrate that ATA is resource-efficient, significantly reducing costs compared to the greedy approach, which can be arbitrarily expensive depending on the number of workers.

NeurIPS Conference 2025 Conference Paper

Dynamic Regret Reduces to Kernelized Static Regret

• Andrew Jacobsen
• Alessandro Rudi
• Francesco Orabona
• Nicolò Cesa-Bianchi

We study dynamic regret in online convex optimization, where the objective is to achieve low cumulative loss relative to an arbitrary benchmark sequence. By observing that competing with an arbitrary sequence of comparators $u_{1}, \ldots, u_{T}$ in $\mathcal{W}\subseteq\mathbb{R}^{d}$ can be reframed as competing with a *fixed* comparator *function* $u: [1, T]\to \mathcal{W}$, we cast dynamic regret minimization as a *static regret* problem in a *function space*. By carefully constructing a suitable function space in the form of a Reproducing Kernel Hilbert Space (RKHS), our reduction enables us to recover the optimal $R_{T}(u_{1}, \ldots, u_{T}) = \mathcal{O}(\sqrt{\sum_{t}\\|u_{t}-u_{t-1}\\|T})$ dynamic regret guarantee in the setting of linear losses, and yields new scale-free and directionally-adaptive dynamic regret guarantees. Moreover, unlike prior dynamic-to-static reductions---which are valid only for linear losses---our reduction holds for *any* sequence of losses, allowing us to recover $\mathcal{O}\big(\\|u\\|^2_{\mathcal{H}}+d_{\mathrm{eff}}(\lambda)\ln T\big)$ bounds when the losses have meaningful curvature, where $d_{\mathrm{eff}}(\lambda)$ is a measure of complexity of the RKHS. Despite working in an infinite-dimensional space, the resulting reduction leads to algorithms that are computable in practice, due to the reproducing property of RKHSs.

NeurIPS Conference 2025 Conference Paper

New Perspectives on the Polyak Stepsize: Surrogate Functions and Negative Results

• Francesco Orabona
• Ryan D'Orazio

The Polyak stepsize has been proven to be a fundamental stepsize in convex optimization, giving near optimal gradient descent rates across a wide range of assumptions. The universality of the Polyak stepsize has also inspired many stochastic variants, with theoretical guarantees and strong empirical performance. Despite the many theoretical results, our understanding of the convergence properties and shortcomings of the Polyak stepsize or its variants is both incomplete and fractured across different analyses. We propose a new, unified, and simple perspective for the Polyak stepsize and its variants as gradient descent on a surrogate loss. We show that each variant is equivalent to minimize a surrogate function with stepsizes that adapt to a guaranteed local curvature. Our general surrogate loss perspective is then used to provide a unified analysis of existing variants across different assumptions. Moreover, we show a number of negative results proving that the non-convergence results in some of the upper bounds is indeed real.

NeurIPS Conference 2025 Conference Paper

Optimal Regret of Bandits under Differential Privacy

• Achraf Azize
• Yulian Wu
• Junya Honda
• Francesco Orabona
• Shinji Ito
• Debabrota Basu

As sequential learning algorithms are increasingly applied to real life, ensuring data privacy while maintaining their utilities emerges as a timely question. In this context, regret minimisation in stochastic bandits under $\epsilon$-global Differential Privacy (DP) has been widely studied. The present literature poses a significant gap between the best-known regret lower and upper bound in this setting, though they ``match in order''. Thus, we revisit the regret lower and upper bounds of $\epsilon$-global DP bandits and improve both. First, we prove a tighter regret lower bound involving a novel information-theoretic quantity characterising the hardness of $\epsilon$-global DP in stochastic bandits. This quantity smoothly interpolates between Kullback–Leibler divergence and Total Variation distance, depending on the privacy budget $\epsilon$. Then, we choose two asymptotically optimal bandit algorithms, i. e. , KL-UCB and IMED, and propose their DP versions using a unified blueprint, i. e. , (a) running in arm-dependent phases, and (b) adding Laplace noise to achieve privacy. For Bernoulli bandits, we analyse the regrets of these algorithms and show that their regrets asymptotically match our lower bound up to a constant arbitrary close to 1. At the core of our algorithms lies a new concentration inequality for sums of Bernoulli variables under Laplace mechanism, which is a new DP version of the Chernoff bound. Finally, our numerical experiments validate that DP-KLUCB and DP-IMED achieve lower regret than the existing $\epsilon$-global DP bandit algorithms.

NeurIPS Conference 2025 Conference Paper

Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Track

• Rylan Schaeffer
• Joshua Kazdan
• Yegor Denisov-Blanch
• Brando Miranda
• Matthias Gerstgrasser
• Susan Zhang
• Andreas Haupt
• Isha Gupta

Science progresses by iteratively advancing and correcting humanity's understanding of the world. In machine learning (ML) research, rapid advancements have led to an explosion of publications, but have also led to misleading, incorrect, flawed or perhaps even fraudulent studies being accepted and sometimes highlighted at ML conferences due to the fallibility of peer review. While such mistakes are understandable, ML conferences do not offer robust processes to help the field systematically correct when such errors are made. This position paper argues that ML conferences should establish a dedicated "Refutations and Critiques" (R&C) Track. This R&C Track would provide a high-profile, reputable platform to support vital research that critically challenges prior research, thereby fostering a dynamic self-correcting research ecosystem. We discuss key considerations including track design, review principles, potential pitfalls, and provide an illustrative example submission concerning a recent ICLR 2025 Oral. We conclude that ML conferences should create official, reputable mechanisms to help ML research self-correct.

ICML Conference 2025 Conference Paper

SquareχPO: Differentially Private and Robust χ2-Preference Optimization in Offline Direct Alignment

• Xingyu Zhou 0001
• Yulian Wu
• Wenqian Weng
• Francesco Orabona

In this paper, we theoretically study the offline alignment of language models with human preference feedback, under both preference label corruption and privacy protections. To this end, we propose a variant of $\chi$PO – Square$\chi$PO, which is a simple one-line change of $\chi$PO with the standard log-loss replaced by a new square loss over probability. Thanks to the inherent nice properties of this new loss, we have advanced the state-of-the-art of differentially private and robust alignment. Specifically, for the local model of label privacy, Square$\chi$PO is the first one that attains optimal rate based on single-policy concentrability even with general function approximations. It also gives the first result under the central model of privacy protection over both prompts (responses) and labels. On the robustness side against Huber label corruption, Square$\chi$PO is the first alignment method that has a meaningful theoretical guarantee under general function approximations. More importantly, Square$\chi$PO can address privacy protection and corruption simultaneously, where an interesting separation is observed, implying that the order of privacy and corruption matters. Furthermore, we show that Square$\chi$PO can also be easily extended to handle the scenario of the general preference model with state-of-the-art guarantees under corruption and privacy. Last but not least, all of our theoretical guarantees enjoy a unified analysis, building upon a new result on the generalization error bounds of least-square regression under corruption and privacy constraints, which we believe is of independent interest to the community.

NeurIPS Conference 2025 Conference Paper

STAR-Bets: Sequential TArget-Recalculating Bets for Tighter Confidence Intervals

• Vaclav Voracek
• Francesco Orabona

The construction of confidence intervals for the mean of a bounded random variable is a classical problem in statistics with numerous applications in machine learning and virtually all scientific fields. In particular, obtaining the tightest possible confidence intervals is vital every time the sampling of the random variables is expensive. The current state-of-the-art method to construct confidence intervals is by using betting algorithms. This is a very successful approach for deriving optimal confidence sequences, even matching the rate of law of iterated logarithms. However, in the fixed horizon setting, these approaches are either sub-optimal or based on heuristic solutions with strong empirical performance but without a finite-time guarantee. Hence, no betting-based algorithm guaranteeing the optimal $\mathcal{O}(\sqrt{\frac{\sigma^2\log\frac1\delta}{n}})$ width of the confidence intervals are known. This work bridges this gap. We propose a betting-based algorithm to compute confidence intervals that empirically outperforms the competitors. Our betting strategy uses the optimal strategy in every step (in a certain sense), whereas the standard betting methods choose a constant strategy in advance. Leveraging this fact results in strict improvements even for classical concentration inequalities, such as the ones of Hoeffding or Bernstein. Moreover, we also prove that the width of our confidence intervals is optimal up to an $1+o(1)$ factor diminishing with $n$.

NeurIPS Conference 2024 Conference Paper

An Equivalence Between Static and Dynamic Regret Minimization

• Andrew Jacobsen
• Francesco Orabona

We study the problem of dynamic regret minimization in online convex optimization, in which the objective is to minimize the difference between the cumulative loss of an algorithm and that of an arbitrary sequence of comparators. While the literature on this topic is very rich, a unifying framework for the analysis and design of these algorithms is still missing. In this paper we show that *for linear losses, dynamic regret minimization is equivalent to static regret minimization in an extended decision space*. Using this simple observation, we show that there is a frontier of lower bounds trading off penalties due to the variance of the losses and penalties due to variability of the comparator sequence, and provide a framework for achieving any of the guarantees along this frontier. As a result, we also prove for the first time that adapting to the squared path-length of an arbitrary sequence of comparators to achieve regret $R_{T}(u_{1}, \dots, u_{T})\le O(\sqrt{T\sum_{t} \\|u_{t}-u_{t+1}\\|^{2}})$ is impossible. However, using our framework we introduce an alternative notion of variability based on a locally-smoothed comparator sequence $\bar u_{1}, \dots, \bar u_{T}$, and provide an algorithm guaranteeing dynamic regret of the form $R_{T}(u_{1}, \dots, u_{T})\le \tilde O(\sqrt{T\sum_{i}\\|\bar u_{i}-\bar u_{i+1}\\|^{2}})$, while still matching in the worst case the usual path-length dependencies up to polylogarithmic terms.

ICLR Conference 2024 Conference Paper

Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion

• Alexandru Meterez
• Amir Joudaki
• Francesco Orabona
• Alexander Immer
• Gunnar Rätsch
• Hadi Daneshmand

Normalization layers are one of the key building blocks for deep neural networks. Several theoretical studies have shown that batch normalization improves the signal propagation, by avoiding the representations from becoming collinear across the layers. However, results on mean-field theory of batch normalization also conclude that this benefit comes at the expense of exploding gradients in depth. Motivated by these two aspects of batch normalization, in this study we pose the following question: *Can a batch-normalized network keep the optimal signal propagation properties, but avoid exploding gradients?* We answer this question in the affirmative by giving a particular construction of an *MLP with linear activations* and batch-normalization that provably has *bounded gradients* at any depth. Based on Weingarten calculus, we develop a rigorous and non-asymptotic theory for this constructed MLP that gives a precise characterization of forward signal propagation, while proving that gradients remain bounded for linearly independent input samples, which holds in most practical settings. Inspired by our theory, we also design an activation shaping scheme that empirically achieves the same properties for non-linear activations.

ICML Conference 2023 Conference Paper

Generalized Implicit Follow-The-Regularized-Leader

• Keyi Chen 0001
• Francesco Orabona

We propose a new class of online learning algorithms, generalized implicit Follow-The-Regularized-Leader (FTRL), that expands the scope of FTRL framework. Generalized implicit FTRL can recover known algorithms, such as FTRL with linearized losses and implicit FTRL, and it allows the design of new update rules, as extensions of aProx and Mirror-Prox to FTRL. Our theory is constructive in the sense that it provides a simple unifying framework to design updates that directly improve the worst-case upper bound on the regret. The key idea is substituting the linearization of the losses with a Fenchel-Young inequality. We show the flexibility of the framework by proving that some known algorithms, like the Mirror-Prox updates, are instantiations of the generalized implicit FTRL. Finally, the new framework allows us to recover the temporal variation bound of implicit OMD, with the same computational complexity.

ICML Conference 2023 Conference Paper

Optimal Stochastic Non-smooth Non-convex Optimization through Online-to-Non-convex Conversion

• Ashok Cutkosky
• Harsh Mehta
• Francesco Orabona

We present new algorithms for optimizing non-smooth, non-convex stochastic objectives based on a novel analysis technique. This improves the current best-known complexity for finding a $(\delta, \epsilon)$-stationary point from $O(\epsilon^{-4}\delta^{-1})$ stochastic gradient queries to $O(\epsilon^{-3}\delta^{-1})$, which we also show to be optimal. Our primary technique is a reduction from non-smooth non-convex optimization to online learning, after which our results follow from standard regret bounds in online learning. For deterministic and second-order smooth objectives, applying more advanced optimistic online learning techniques enables a new complexity of $O(\epsilon^{-1. 5}\delta^{-0. 5})$. Our improved non-smooth analysis also immediately recovers all optimal or best-known results for finding $\epsilon$ stationary points of smooth or second-order smooth objectives in both stochastic and deterministic settings.

AAAI Conference 2022 Conference Paper

Better Parameter-Free Stochastic Optimization with ODE Updates for Coin-Betting

• Keyi Chen
• John Langford
• Francesco Orabona

Parameter-free stochastic gradient descent (PFSGD) algorithms do not require setting learning rates while achieving optimal theoretical performance. In practical applications, however, there remains an empirical gap between tuned stochastic gradient descent (SGD) and PFSGD. In this paper, we close the empirical gap with a new parameter-free algorithm based on continuous-time Coin-Betting on truncated models. The new update is derived through the solution of an Ordinary Differential Equation (ODE) and solved in a closed form. We show empirically that this new parameter-free algorithm outperforms algorithms with the “best default” learning rates and almost matches the performance of finely tuned baselines without anything to tune.

NeurIPS Conference 2022 Conference Paper

Robustness to Unbounded Smoothness of Generalized SignSGD

• Michael Crawshaw
• Mingrui Liu
• Francesco Orabona
• Wei Zhang
• Zhenxun Zhuang

Traditional analyses in non-convex optimization typically rely on the smoothness assumption, namely requiring the gradients to be Lipschitz. However, recent evidence shows that this smoothness condition does not capture the properties of some deep learning objective functions, including the ones involving Recurrent Neural Networks and LSTMs. Instead, they satisfy a much more relaxed condition, with potentially unbounded smoothness. Under this relaxed assumption, it has been theoretically and empirically shown that the gradient-clipped SGD has an advantage over the vanilla one. In this paper, we show that clipping is not indispensable for Adam-type algorithms in tackling such scenarios: we theoretically prove that a generalized SignSGD algorithm can obtain similar convergence rates as SGD with clipping but does not need explicit clipping at all. This family of algorithms on one end recovers SignSGD and on the other end closely resembles the popular Adam algorithm. Our analysis underlines the critical role that momentum plays in analyzing SignSGD-type and Adam-type algorithms: it not only reduces the effects of noise, thus removing the need for large mini-batch in previous analyses of SignSGD-type algorithms, but it also substantially reduces the effects of unbounded smoothness and gradient norms. To the best of our knowledge, this work is the first one showing the benefit of Adam-type algorithms compared with non-adaptive gradient algorithms such as gradient descent in the unbounded smoothness setting. We also compare these algorithms with popular optimizers on a set of deep learning tasks, observing that we can match the performance of Adam while beating others.

TMLR Journal 2022 Journal Article

Understanding AdamW through Proximal Methods and Scale-Freeness

• Zhenxun Zhuang
• Mingrui Liu
• Ashok Cutkosky
• Francesco Orabona

Adam has been widely adopted for training deep neural networks due to less hyperparameter tuning and remarkable performance. To improve generalization, Adam is typically used in tandem with a squared $\ell_2$ regularizer (referred to as Adam-$\ell_2$). However, even better performance can be obtained with AdamW, which decouples the gradient of the regularizer from the update rule of Adam-$\ell_2$. Yet, we are still lacking a complete explanation of the advantages of AdamW. In this paper, we tackle this question from both an optimization and an empirical point of view. First, we show how to re-interpret AdamW as an approximation of a proximal gradient method, which takes advantage of the closed-form proximal mapping of the regularizer instead of only utilizing its gradient information as in Adam-$\ell_2$. Next, we consider the property of "scale-freeness" enjoyed by AdamW and by its proximal counterpart: their updates are invariant to component-wise rescaling of the gradients. We provide empirical evidence across a wide range of deep learning experiments showing a correlation between the problems in which AdamW exhibits an advantage over Adam-$\ell_2$ and the degree to which we expect the gradients of the network to exhibit multiple scales, thus motivating the hypothesis that the advantage of AdamW could be due to the scale-free updates.

ICML Conference 2021 Conference Paper

A Second look at Exponential and Cosine Step Sizes: Simplicity, Adaptivity, and Performance

• Xiaoyu Li
• Zhenxun Zhuang
• Francesco Orabona

Stochastic Gradient Descent (SGD) is a popular tool in training large-scale machine learning models. Its performance, however, is highly variable, depending crucially on the choice of the step sizes. Accordingly, a variety of strategies for tuning the step sizes have been proposed, ranging from coordinate-wise approaches (a. k. a. “adaptive” step sizes) to sophisticated heuristics to change the step size in each iteration. In this paper, we study two step size schedules whose power has been repeatedly confirmed in practice: the exponential and the cosine step sizes. For the first time, we provide theoretical support for them proving convergence rates for smooth non-convex functions, with and without the Polyak-Ł{}ojasiewicz (PL) condition. Moreover, we show the surprising property that these two strategies are \emph{adaptive} to the noise level in the stochastic gradients of PL functions. That is, contrary to polynomial step sizes, they achieve almost optimal performance without needing to know the noise level nor tuning their hyperparameters based on it. Finally, we conduct a fair and comprehensive empirical evaluation of real-world datasets with deep learning architectures. Results show that, even if only requiring at most two hyperparameters to tune, these two strategies best or match the performance of various finely-tuned state-of-the-art strategies.

NeurIPS Conference 2021 Conference Paper

Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers

• Jeffrey Negrea
• Blair Bilodeau
• Nicolò Campolongo
• Francesco Orabona
• Dan Roy

Quantile (and, more generally, KL) regret bounds, such as those achieved by NormalHedge (Chaudhuri, Freund, and Hsu 2009) and its variants, relax the goal of competing against the best individual expert to only competing against a majority of experts on adversarial data. More recently, the semi-adversarial paradigm (Bilodeau, Negrea, and Roy 2020) provides an alternative relaxation of adversarial online learning by considering data that may be neither fully adversarial nor stochastic (I. I. D. ). We achieve the minimax optimal regret in both paradigms using FTRL with separate, novel, root-logarithmic regularizers, both of which can be interpreted as yielding variants of NormalHedge. We extend existing KL regret upper bounds, which hold uniformly over target distributions, to possibly uncountable expert classes with arbitrary priors; provide the first full-information lower bounds for quantile regret on finite expert classes (which are tight); and provide an adaptively minimax optimal algorithm for the semi-adversarial paradigm that adapts to the true, unknown constraint faster, leading to uniformly improved regret bounds over existing methods.

ICML Conference 2021 Conference Paper

Online Learning with Optimism and Delay

• Genevieve Flaspohler
• Francesco Orabona
• Judah Cohen
• Soukayna Mouatadid
• Miruna Oprescu
• Paulo Orenstein
• Lester W. Mackey

Inspired by the demands of real-time climate and weather forecasting, we develop optimistic online learning algorithms that require no parameter tuning and have optimal regret guarantees under delayed feedback. Our algorithms—DORM, DORM+, and AdaHedgeD—arise from a novel reduction of delayed online learning to optimistic online learning that reveals how optimistic hints can mitigate the regret penalty caused by delay. We pair this delay-as-optimism perspective with a new analysis of optimistic learning that exposes its robustness to hinting errors and a new meta-algorithm for learning effective hinting strategies in the presence of delay. We conclude by benchmarking our algorithms on four subseasonal climate forecasting tasks, demonstrating low regret relative to state-of-the-art forecasting models.

NeurIPS Conference 2020 Conference Paper

Temporal Variability in Implicit Online Learning

• Nicolò Campolongo
• Francesco Orabona

In the setting of online learning, Implicit algorithms turn out to be highly successful from a practical standpoint. However, the tightest regret analyses only show marginal improvements over Online Mirror Descent. In this work, we shed light on this behavior carrying out a careful regret analysis. We prove a novel static regret bound that depends on the temporal variability of the sequence of loss functions, a quantity which is often encountered when considering dynamic competitors. We show, for example, that the regret can be constant if the temporal variability is constant and the learning rate is tuned appropriately, without the need of smooth losses. Moreover, we present an adaptive algorithm that achieves this regret bound without prior knowledge of the temporal variability and prove a matching lower bound. Finally, we validate our theoretical findings on classification and regression datasets.

NeurIPS Conference 2019 Conference Paper

Kernel Truncated Randomized Ridge Regression: Optimal Rates and Low Noise Acceleration

• Kwang-Sung Jun
• Ashok Cutkosky
• Francesco Orabona

In this paper we consider the nonparametric least square regression in a Reproducing Kernel Hilbert Space (RKHS). We propose a new randomized algorithm that has optimal generalization error bounds with respect to the square loss, closing a long-standing gap between upper and lower bounds. Moreover, we show that our algorithm has faster finite-time and asymptotic rates on problems where the Bayes risk with respect to the square loss is small. We state our results using standard tools from the theory of least square regression in RKHSs, namely, the decay of the eigenvalues of the associated integral operator and the complexity of the optimal predictor measured through the integral operator.

NeurIPS Conference 2019 Conference Paper

Momentum-Based Variance Reduction in Non-Convex SGD

• Ashok Cutkosky
• Francesco Orabona

Variance reduction has emerged in recent years as a strong competitor to stochastic gradient descent in non-convex problems, providing the first algorithms to improve upon the converge rate of stochastic gradient descent for finding first-order critical points. However, variance reduction techniques typically require carefully tuned learning rates and willingness to use excessively large "mega-batches" in order to achieve their improved results. We present a new algorithm, STORM, that does not require any batches and makes use of adaptive learning rates, enabling simpler implementation and less hyperparameter tuning. Our technique for removing the batches uses a variant of momentum to achieve variance reduction in non-convex optimization. On smooth losses $F$, STORM finds a point $x$ with $\mathbb{E}[\|\nabla F(x)\|]\le O(1/\sqrt{T}+\sigma^{1/3}/T^{1/3})$ in $T$ iterations with $\sigma^2$ variance in the gradients, matching the best-known rate but without requiring knowledge of $\sigma$.

ICML Conference 2019 Conference Paper

Surrogate Losses for Online Learning of Stepsizes in Stochastic Non-Convex Optimization

• Zhenxun Zhuang
• Ashok Cutkosky
• Francesco Orabona

Stochastic Gradient Descent (SGD) has played a central role in machine learning. However, it requires a carefully hand-picked stepsize for fast convergence, which is notoriously tedious and time-consuming to tune. Over the last several years, a plethora of adaptive gradient-based algorithms have emerged to ameliorate this problem. In this paper, we propose new surrogate losses to cast the problem of learning the optimal stepsizes for the stochastic optimization of a non-convex smooth objective function onto an online convex optimization problem. This allows the use of no-regret online algorithms to compute optimal stepsizes on the fly. In turn, this results in a SGD algorithm with self-tuned stepsizes that guarantees convergence rates that are automatically adaptive to the level of noise.

TCS Journal 2018 Journal Article

Scale-free online learning

• Francesco Orabona
• Dávid Pál

We design and analyze algorithms for online linear optimization that have optimal regret and at the same time do not need to know any upper or lower bounds on the norm of the loss vectors. Our algorithms are instances of the Follow the Regularized Leader (FTRL) and Mirror Descent (MD) meta-algorithms. We achieve adaptiveness to the norms of the loss vectors by scale invariance, i. e. , our algorithms make exactly the same decisions if the sequence of loss vectors is multiplied by any positive constant. The algorithm based on FTRL works for any decision set, bounded or unbounded. For unbounded decisions sets, this is the first adaptive algorithm for online linear optimization with a non-vacuous regret bound. In contrast, we show lower bounds on scale-free algorithms based on MD on unbounded domains.

ICML Conference 2017 Conference Paper

Efficient Online Bandit Multiclass Learning with Õ(√T) Regret

• Alina Beygelzimer
• Francesco Orabona
• Chicheng Zhang

We present an efficient second-order algorithm with $\tilde{O}(1/\eta \sqrt{T})$ regret for the bandit online multiclass problem. The regret bound holds simultaneously with respect to a family of loss functions parameterized by $\eta$, ranging from hinge loss ($\eta=0$) to squared hinge loss ($\eta=1$). This provides a solution to the open problem of (Abernethy, J. and Rakhlin, A. An efficient bandit algorithm for $\sqrt{T}$-regret in online multiclass prediction? In COLT, 2009). We test our algorithm experimentally, showing that it performs favorably against earlier algorithms.

NeurIPS Conference 2017 Conference Paper

Training Deep Networks without Learning Rates Through Coin Betting

• Francesco Orabona
• Tatiana Tommasi

Deep learning methods achieve state-of-the-art performance in many application scenarios. Yet, these methods require a significant amount of hyperparameters tuning in order to achieve the best results. In particular, tuning the learning rates in the stochastic optimization process is still one of the main bottlenecks. In this paper, we propose a new stochastic gradient descent procedure for deep networks that does not require any learning rate setting. Contrary to previous methods, we do not adapt the learning rates nor we make use of the assumed curvature of the objective function. Instead, we reduce the optimization process to a game of betting on a coin and propose a learning rate free optimal algorithm for this scenario. Theoretical convergence is proven for convex and quasi-convex functions and empirical evidence shows the advantage of our algorithm over popular stochastic gradient algorithms.

NeurIPS Conference 2016 Conference Paper

Coin Betting and Parameter-Free Online Learning

• Francesco Orabona
• David Pal

In the recent years, a number of parameter-free algorithms have been developed for online linear optimization over Hilbert spaces and for learning with expert advice. These algorithms achieve optimal regret bounds that depend on the unknown competitors, without having to tune the learning rates with oracle choices. We present a new intuitive framework to design parameter-free algorithms for both online linear optimization over Hilbert spaces and for learning with expert advice, based on reductions to betting on outcomes of adversarial coins. We instantiate it using a betting algorithm based on the Krichevsky-Trofimov estimator. The resulting algorithms are simple, with no parameters to be tuned, and they improve or match previous results in terms of regret guarantee and per-round complexity.

ICML Conference 2016 Conference Paper

Solving Ridge Regression using Sketched Preconditioned SVRG

• Alon Gonen
• Francesco Orabona
• Shai Shalev-Shwartz

We develop a novel preconditioning method for ridge regression, based on recent linear sketching methods. By equipping Stochastic Variance Reduced Gradient (SVRG) with this preconditioning process, we obtain a significant speed-up relative to fast stochastic methods such as SVRG, SDCA and SAG.

ICML Conference 2014 Conference Paper

On Measure Concentration of Random Maximum A-Posteriori Perturbations

• Francesco Orabona
• Tamir Hazan
• Anand D. Sarwate
• Tommi S. Jaakkola

The maximum a-posteriori (MAP) perturbation framework has emerged as a useful approach for inference and learning in high dimensional complex models. By maximizing a randomly perturbed potential function, MAP perturbations generate unbiased samples from the Gibbs distribution. Unfortunately, the computational cost of generating so many high-dimensional random variables can be prohibitive. More efficient algorithms use sequential sampling strategies based on the expected value of low dimensional MAP perturbations. This paper develops new measure concentration inequalities that bound the number of samples needed to estimate such expected values. Applying the general result to MAP perturbations can yield a more efficient algorithm to approximate sampling from the Gibbs distribution. The measure concentration result is of general interest and may be applicable to other areas involving Monte Carlo estimation of expectations.

JMLR Journal 2014 Journal Article

On Multilabel Classification and Ranking with Bandit Feedback

• Claudio Gentile
• Francesco Orabona

We present a novel multilabel/ranking algorithm working in partial information settings. The algorithm is based on 2nd- order descent methods, and relies on upper-confidence bounds to trade-off exploration and exploitation. We analyze this algorithm in a partial adversarial setting, where covariates can be adversarial, but multilabel probabilities are ruled by (generalized) linear models. We show $O(T^{1/2}\log T)$ regret bounds, which improve in several ways on the existing results. We test the effectiveness of our upper-confidence scheme by contrasting against full-information baselines on diverse real- world multilabel data sets, often obtaining comparable performance. [abs] [ pdf ][ bib ] &copy JMLR 2014. ( edit, beta )

NeurIPS Conference 2014 Conference Paper

Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learning

• Francesco Orabona

Stochastic gradient descent algorithms for training linear and kernel predictors are gaining more and more importance, thanks to their scalability. While various methods have been proposed to speed up their convergence, the model selection phase is often ignored. In fact, in theoretical works most of the time assumptions are made, for example, on the prior knowledge of the norm of the optimal solution, while in the practical world validation methods remain the only viable approach. In this paper, we propose a new kernel-based stochastic gradient descent algorithm that performs model selection while training, with no parameters to tune, nor any form of cross-validation. The algorithm builds on recent advancement in online learning theory for unconstrained settings, to estimate over time the right regularization in a data-dependent way. Optimal rates of convergence are proved under standard smoothness assumptions on the target function as well as preliminary empirical results.

NeurIPS Conference 2013 Conference Paper

Dimension-Free Exponentiated Gradient

• Francesco Orabona

We present a new online learning algorithm that extends the exponentiated gradient to infinite dimensional spaces. Our analysis shows that the algorithm is implicitly able to estimate the $L_2$ norm of the unknown competitor, $U$, achieving a regret bound of the order of $O(U \log (U T+1))\sqrt{T})$, instead of the standard $O((U^2 +1) \sqrt{T})$, achievable without knowing $U$. For this analysis, we introduce novel tools for algorithms with time-varying regularizers, through the use of local smoothness. Through a lower bound, we also show that the algorithm is optimal up to $\sqrt{\log T}$ term for linear and Lipschitz losses.

NeurIPS Conference 2013 Conference Paper

Regression-tree Tuning in a Streaming Setting

• Samory Kpotufe
• Francesco Orabona

We consider the problem of maintaining the data-structures of a partition-based regression procedure in a setting where the training data arrives sequentially over time. We prove that it is possible to maintain such a structure in time $O(\log n)$ at any time step $n$ while achieving a nearly-optimal regression rate of $\tilde{O}(n^{-2/(2+d)})$ in terms of the unknown metric dimension $d$. Finally we prove a new regression lower-bound which is independent of a given data size, and hence is more appropriate for the streaming setting.

ICML Conference 2013 Conference Paper

Stability and Hypothesis Transfer Learning

• Ilja Kuzborskij
• Francesco Orabona

We consider the transfer learning scenario, where the learner does not have access to the source domain directly, but rather operates on the basis of hypotheses induced from it – the Hypothesis Transfer Learning (HTL) problem. Particularly, we conduct a theoretical analysis of HTL by considering the algorithmic stability of a class of HTL algorithms based on Regularized Least Squares with biased regularization. We show that the relatedness of source and target domains accelerates the convergence of the Leave-One-Out error to the generalization error, thus enabling the use of the Leave-One-Out error to find the optimal transfer parameters, even in the presence of a small training set. In case of unrelated domains we also suggest a theoretically principled way to prevent negative transfer, so that in the limit we recover the performance of the algorithm not using any knowledge from the source domain.

JMLR Journal 2012 Journal Article

Multi Kernel Learning with Online-Batch Optimization

• Francesco Orabona
• Luo Jie
• Barbara Caputo

In recent years there has been a lot of interest in designing principled classification algorithms over multiple cues, based on the intuitive notion that using more features should lead to better performance. In the domain of kernel methods, a principled way to use multiple features is the Multi Kernel Learning (MKL) approach. Here we present a MKL optimization algorithm based on stochastic gradient descent that has a guaranteed convergence rate. We directly solve the MKL problem in the primal formulation. By having a p-norm formulation of MKL, we introduce a parameter that controls the level of sparsity of the solution, while leading to an easier optimization problem. We prove theoretically and experimentally that 1) our algorithm has a faster convergence rate as the number of kernels grows; 2) the training complexity is linear in the number of training examples; 3) very few iterations are sufficient to reach good solutions. Experiments on standard benchmark databases support our claims. [abs] [ pdf ][ bib ] &copy JMLR 2012. ( edit, beta )

NeurIPS Conference 2012 Conference Paper

On Multilabel Classification and Ranking with Partial Feedback

• Claudio Gentile
• Francesco Orabona

We present a novel multilabel/ranking algorithm working in partial information settings. The algorithm is based on 2nd-order descent methods, and relies on upper-confidence bounds to trade-off exploration and exploitation. We analyze this algorithm in a partial adversarial setting, where covariates can be adversarial, but multilabel probabilities are ruled by (generalized) linear models. We show $O(T^{1/2}\log T)$ regret bounds, which improve in several ways on the existing results. We test the effectiveness of our upper-confidence scheme by contrasting against full-information baselines on real-world multilabel datasets, often obtaining comparable performance.

ICML Conference 2011 Conference Paper

Better Algorithms for Selective Sampling

• Francesco Orabona
• Nicolò Cesa-Bianchi

ICML Conference 2011 Conference Paper

Ultra-Fast Optimization Algorithm for Sparse Multi Kernel Learning

• Francesco Orabona
• Jie Luo

NeurIPS Conference 2010 Conference Paper

Learning from Candidate Labeling Sets

• Jie Luo
• Francesco Orabona

In many real world applications we do not have access to fully-labeled training data, but only to a list of possible labels. This is the case, e. g. , when learning visual classifiers from images downloaded from the web, using just their text captions or tags as learning oracles. In general, these problems can be very difficult. However most of the time there exist different implicit sources of information, coming from the relations between instances and labels, which are usually dismissed. In this paper, we propose a semi-supervised framework to model this kind of problems. Each training sample is a bag containing multi-instances, associated with a set of candidate labeling vectors. Each labeling vector encodes the possible labels for the instances in the bag, with only one being fully correct. The use of the labeling vectors provides a principled way not to exclude any information. We propose a large margin discriminative formulation, and an efficient algorithm to solve it. Experiments conducted on artificial datasets and a real-world images and captions dataset show that our approach achieves performance comparable to SVM trained with the ground-truth labels, and outperforms other baselines.

NeurIPS Conference 2010 Conference Paper

New Adaptive Algorithms for Online Classification

• Francesco Orabona
• Koby Crammer

We propose a general framework to online learning for classification problems with time-varying potential functions in the adversarial setting. This framework allows to design and prove relative mistake bounds for any generic loss function. The mistake bounds can be specialized for the hinge loss, allowing to recover and improve the bounds of known online classification algorithms. By optimizing the general bound we derive a new online classification algorithm, called NAROW, that hybridly uses adaptive- and fixed- second order information. We analyze the properties of the algorithm and illustrate its performance using synthetic dataset.

JMLR Journal 2009 Journal Article

Bounded Kernel-Based Online Learning

• Francesco Orabona
• Joseph Keshet
• Barbara Caputo

A common problem of kernel-based online algorithms, such as the kernel-based Perceptron algorithm, is the amount of memory required to store the online hypothesis, which may increase without bound as the algorithm progresses. Furthermore, the computational load of such algorithms grows linearly with the amount of memory used to store the hypothesis. To attack these problems, most previous work has focused on discarding some of the instances, in order to keep the memory bounded. In this paper we present a new algorithm, in which the instances are not discarded, but are instead projected onto the space spanned by the previous online hypothesis. We call this algorithm Projectron. While the memory size of the Projectron solution cannot be predicted before training, we prove that its solution is guaranteed to be bounded. We derive a relative mistake bound for the proposed algorithm, and deduce from it a slightly different algorithm which outperforms the Perceptron. We call this second algorithm Projectron++. We show that this algorithm can be extended to handle the multiclass and the structured output settings, resulting, as far as we know, in the first online bounded algorithm that can learn complex classification tasks. The method of bounding the hypothesis representation can be applied to any conservative online algorithm and to other online algorithms, as it is demonstrated for ALMA 2. Experimental results on various data sets show the empirical advantage of our technique compared to various bounded online algorithms, both in terms of memory and accuracy. [abs] [ pdf ][ bib ] &copy JMLR 2009. ( edit, beta )

ICRA Conference 2009 Conference Paper

Model adaptation with least-squares SVM for adaptive hand prosthetics

• Francesco Orabona
• Claudio Castellini
• Barbara Caputo
• Angelo Emanuele Fiorilla
• Giulio Sandini

The state-of-the-art in control of hand prosthetics is far from optimal. The main control interface is represented by surface electromyography (EMG): the activation potentials of the remnants of large muscles of the stump are used in a non-natural way to control one or, at best, two degrees-of-freedom. This has two drawbacks: first, the dexterity of the prosthesis is limited, leading to poor interaction with the environment; second, the patient undergoes a long training time. As more dexterous hand prostheses are put on the market, the need for a finer and more natural control arises. Machine learning can be employed to this end. A desired feature is that of providing a pre-trained model to the patient, so that a quicker and better interaction can be obtained. To this end we propose model adaptation with least-squares SVMs, a technique that allows the automatic tuning of the degree of adaptation. We test the effectiveness of the approach on a database of EMG signals gathered from human subjects. We show that, when pre-trained models are used, the number of training samples needed to reach a certain performance is reduced, and the overall performance is increased, compared to what would be achieved by starting from scratch.

ICML Conference 2009 Conference Paper

Robust bounds for classification via selective sampling

• Nicolò Cesa-Bianchi
• Claudio Gentile
• Francesco Orabona

We introduce a new algorithm for binary classification in the selective sampling protocol. Our algorithm uses Regularized Least Squares (RLS) as base classifier, and for this reason it can be efficiently run in any RKHS. Unlike previous margin-based semi-supervised algorithms, our sampling condition hinges on a simultaneous upper bound on bias and variance of the RLS estimate under a simple linear label noise model. This fact allows us to prove performance bounds that hold for an arbitrary sequence of instances. In particular, we show that our sampling strategy approximates the margin of the Bayes optimal classifier to any desired accuracy ε by asking Õ ( d /ε 2 ) queries (in the RKHS case d is replaced by a suitable spectral quantity). While these are the standard rates in the fully supervised i.i.d. case, the best previously known result in our harder setting was Õ ( d 3 /ε 4 ). Preliminary experiments show that some of our algorithms also exhibit a good practical performance.

IROS Conference 2009 Conference Paper

You live, you learn, you forget: Continuous learning of visual places with a forgetting mechanism

• Muhammad Muneeb Ullah
• Francesco Orabona
• Barbara Caputo

To fulfill the dream of having autonomous robots at home, there is a need for spatial representations augmented with semantic concepts. Vision has emerged recently as the key modality to recognize semantic categories like places (office, corridor, kitchen, etc). A crucial aspect of these semantic place representations is that they change over time, due to the dynamism of the world. This calls for visual algorithms able to learn from experience while at the same time managing the continuous flow of incoming data. This paper addresses these issues by presenting an SVM-based algorithm able to (a) learn continuously from experience with a fast updating rule, and (b) control the memory growth via a random forgetting mechanism while at the same time preserving an accuracy comparable to that of the batch algorithm. We apply our method to two different scenarios where learning from experience plays an important role: (1) continuous learning of visual places under dynamic changes, and (2) knowledge transfer of visual concepts across robot platforms. For both scenarios, results confirm the effectiveness of our approach.

ICML Conference 2008 Conference Paper

The projectron: a bounded kernel-based Perceptron

• Francesco Orabona
• Joseph Keshet
• Barbara Caputo

We present a discriminative online algorithm with a bounded memory growth, which is based on the kernel-based Perceptron. Generally, the required memory of the kernel-based Perceptron for storing the online hypothesis is not bounded. Previous work has been focused on discarding part of the instances in order to keep the memory bounded. In the proposed algorithm the instances are not discarded, but projected onto the space spanned by the previous online hypothesis. We derive a relative mistake bound and compare our algorithm both analytically and empirically to the state-of-the-art Forgetron algorithm (Dekel et al, 2007). The first variant of our algorithm, called Projectron, outperforms the Forgetron. The second variant, called Projectron++, outperforms even the Perceptron.