Umar Syed

NeurIPS Conference 2025 Conference Paper

Escaping Collapse: The Strength of Weak Data for Large Language Model Training

• Kareem Amin
• Sara Babakniya
• Alex Bie
• Weiwei Kong
• Umar Syed
• Sergei Vassilvitskii

Synthetically-generated data plays an increasingly larger role in training large language models. However, while synthetic data has been found to be useful, studies have also shown that without proper curation it can cause LLM performance to plateau, or even "collapse", after many training iterations. In this paper, we formalize this question and develop a theoretical framework to investigate how much curation is needed in order to ensure that LLM performance continually improves. Our analysis is inspired by boosting, a classic machine learning technique that leverages a very weak learning algorithm to produce an arbitrarily good classifier. The approach we analyze subsumes many recently proposed methods for training LLMs on synthetic data, and thus our analysis sheds light on why they are successful, and also suggests opportunities for future improvement. We present experiments that validate our theory, and show that dynamically focusing labeling resources on the most challenging examples --- in much the same way that boosting focuses the efforts of the weak learner --- leads to improved performance.

ICML Conference 2023 Conference Paper

Label differential privacy and private training data release

• Róbert Busa-Fekete
• Andres Muñoz Medina
• Umar Syed
• Sergei Vassilvitskii

We study differentially private mechanisms for sharing training data in machine learning settings. Our goal is to enable learning of an accurate predictive model while protecting the privacy of each user’s label. Previous work established privacy guarantees that assumed the features are public and given exogenously, a setting known as label differential privacy. In some scenarios, this can be a strong assumption that removes the interplay between features and labels from the privacy analysis. We relax this approach and instead assume the features are drawn from a distribution that depends on the private labels. We first show that simply adding noise to the label, as in previous work, can lead to an arbitrarily weak privacy guarantee, and also present methods for estimating this privacy loss from data. We then present a new mechanism that replaces some training examples with synthetically generated data, and show that our mechanism has a much better privacy-utility tradeoff if the synthetic data is ‘realistic’, in a certain quantifiable sense. Finally, we empirically validate our theoretical analysis.

NeurIPS Conference 2022 Conference Paper

Private and Communication-Efficient Algorithms for Entropy Estimation

• Gecia Bravo-Hermsdorff
• Róbert Busa-Fekete
• Mohammad Ghavamzadeh
• Andres Munoz Medina
• Umar Syed

Modern statistical estimation is often performed in a distributed setting where each sample belongs to single user who shares their data with a central server. Users are typically concerned with preserving the privacy of their sample, and also with minimizing the amount of data they must transmit to the server. We give improved private and communication-efficient algorithms for estimating several popular measures of the entropy of a distribution. All of our algorithms have constant communication cost and satisfy local differential privacy. For a joint distribution on many variables whose conditional independence graph is a tree, we describe algorithms for estimating Shannon entropy that require a number of samples that is linear in the number of variables, compared to the quadratic sample complexity of prior work. We also describe an algorithm for estimating Gini entropy whose sample complexity has no dependence on the support size of the distribution and can be implemented using a single round of concurrent communication between the users and the server, while the previously best-known algorithm has high communication cost and requires the server to facilitate interaction between the users. Finally, we describe an algorithm for estimating collision entropy that matches the space and sample complexity of the best known algorithm but generalizes it to the private and communication-efficient setting.

NeurIPS Conference 2017 Conference Paper

Statistical Cost Sharing

• Eric Balkanski
• Umar Syed
• Sergei Vassilvitskii

We study the cost sharing problem for cooperative games in situations where the cost function C is not available via oracle queries, but must instead be learned from samples drawn from a distribution, represented as tuples (S, C(S)), for different subsets S of players. We formalize this approach, which we call statistical cost sharing, and consider the computation of the core and the Shapley value. Expanding on the work by Balcan et al, we give precise sample complexity bounds for computing cost shares that satisfy the core property with high probability for any function with a non-empty core. For the Shapley value, which has never been studied in this setting, we show that for submodular cost functions with curvature bounded curvature kappa it can be approximated from samples from the uniform distribution to a sqrt{1 - kappa} factor, and that the bound is tight. We then define statistical analogues of the Shapley axioms, and derive a notion of statistical Shapley value and that these can be approximated arbitrarily well from samples from any distribution and for any function.

ICML Conference 2016 Conference Paper

Pricing a Low-regret Seller

• Hoda Heidari
• Mohammad Mahdian
• Umar Syed
• Sergei Vassilvitskii
• Sadra Yazdanbod

As the number of ad exchanges has grown, publishers have turned to low regret learning algorithms to decide which exchange offers the best price for their inventory. This in turn opens the following question for the exchange: how to set prices to attract as many sellers as possible and maximize revenue. In this work we formulate this precisely as a learning problem, and present algorithms showing that by simply knowing that the counterparty is using a low regret algorithm is enough for the exchange to have its own low regret learning algorithm to find the optimal price.

ICML Conference 2015 Conference Paper

Structural Maxent Models

• Corinna Cortes
• Vitaly Kuznetsov
• Mehryar Mohri
• Umar Syed

We present a new class of density estimation models, Structural Maxent models, with feature functions selected from possibly very complex families. The design of our models is motivated by data-dependent convergence bounds and benefits from new data-dependent learning bounds expressed in terms of the Rademacher complexities of the sub-families composing the family of features considered. We prove a duality theorem, which we use to derive our Structural Maxent algorithm. We give a full description of our algorithm, including the details of its derivation and report the results of several experiments demonstrating that its performance compares favorably to that of existing regularized Maxent. We further similarly define conditional Structural Maxent models for multi-class classification problems. These are conditional probability models making use of possibly complex feature families. We also prove a duality theorem for these models which shows the connection between these models and existing binary and multi-class deep boosting algorithms.

ICML Conference 2014 Conference Paper

Deep Boosting

• Corinna Cortes
• Mehryar Mohri
• Umar Syed

We present a new ensemble learning algorithm, DeepBoost, which can use as base classifiers a hypothesis set containing deep decision trees, or members of other rich or complex families, and succeed in achieving high accuracy without overfitting the data. The key to the success of the algorithm is a ‘capacity-conscious’ criterion for the selection of the hypotheses. We give new data-dependent learning bounds for convex ensembles expressed in terms of the Rademacher complexities of the sub-families composing the base classifier set, and the mixture weight assigned to each sub-family. Our algorithm directly benefits from these guarantees since it seeks to minimize the corresponding learning bound. We give a full description of our algorithm, including the details of its derivation, and report the results of several experiments showing that its performance compares favorably to that of AdaBoost and Logistic Regression and their L_1-regularized variants.

NeurIPS Conference 2014 Conference Paper

Multi-Class Deep Boosting

• Vitaly Kuznetsov
• Mehryar Mohri
• Umar Syed

We present new ensemble learning algorithms for multi-class classification. Our algorithms can use as a base classifier set a family of deep decision trees or other rich or complex families and yet benefit from strong generalization guarantees. We give new data-dependent learning bounds for convex ensembles in the multi-class classification setting expressed in terms of the Rademacher complexities of the sub-families composing the base classifier set, and the mixture weight assigned to each sub-family. These bounds are finer than existing ones both thanks to an improved dependency on the number of classes and, more crucially, by virtue of a more favorable complexity term expressed as an average of the Rademacher complexities based on the ensemble’s mixture weights. We introduce and discuss several new multi-class ensemble algorithms benefiting from these guarantees, prove positive results for the H-consistency of several of them, and report the results of experiments showing that their performance compares favorably with that of multi-class versions of AdaBoost and Logistic Regression and their L1-regularized counterparts.

NeurIPS Conference 2014 Conference Paper

Repeated Contextual Auctions with Strategic Buyers

• Kareem Amin
• Afshin Rostamizadeh
• Umar Syed

Motivated by real-time advertising exchanges, we analyze the problem of pricing inventory in a repeated posted-price auction. We consider both the cases of a truthful and surplus-maximizing buyer, where the former makes decisions myopically on every round, and the latter may strategically react to our algorithm, forgoing short-term surplus in order to trick the algorithm into setting better prices in the future. We further assume a buyer’s valuation of a good is a function of a context vector that describes the good being sold. We give the first algorithm attaining sublinear (O(T^{2/3})) regret in the contextual setting against a surplus-maximizing buyer. We also extend this result to repeated second-price auctions with multiple buyers.

NeurIPS Conference 2013 Conference Paper

Learning Prices for Repeated Auctions with Strategic Buyers

• Kareem Amin
• Afshin Rostamizadeh
• Umar Syed

Inspired by real-time ad exchanges for online display advertising, we consider the problem of inferring a buyer's value distribution for a good when the buyer is repeatedly interacting with a seller through a posted-price mechanism. We model the buyer as a strategic agent, whose goal is to maximize her long-term surplus, and we are interested in mechanisms that maximize the seller's long-term revenue. We present seller algorithms that are no-regret when the buyer discounts her future surplus --- i. e. the buyer prefers showing advertisements to users sooner rather than later. We also give a lower bound on regret that increases as the buyer's discounting weakens and shows, in particular, that any seller algorithm will suffer linear regret if there is no discounting.

UAI Conference 2011 Conference Paper

Graphical Models for Bandit Problems

• Kareem Amin 0002
• Michael J. Kearns
• Umar Syed

NeurIPS Conference 2010 Conference Paper

A Reduction from Apprenticeship Learning to Classification

• Umar Syed
• Robert Schapire

We provide new theoretical results for apprenticeship learning, a variant of reinforcement learning in which the true reward function is unknown, and the goal is to perform well relative to an observed expert. We study a common approach to learning from expert demonstrations: using a classification algorithm to learn to imitate the expert's behavior. Although this straightforward learning strategy is widely-used in practice, it has been subject to very little formal analysis. We prove that, if the learned classifier has error rate $\eps$, the difference between the value of the apprentice's policy and the expert's policy is $O(\sqrt{\eps})$. Further, we prove that this difference is only $O(\eps)$ when the expert's policy is close to optimal. This latter result has an important practical consequence: Not only does imitating a near-optimal expert result in a better policy, but far fewer demonstrations are required to successfully imitate such an expert. This suggests an opportunity for substantial savings whenever the expert is known to be good, but demonstrations are expensive or difficult to obtain.

AAAI Conference 2010 Conference Paper

Private and Third-Party Randomization in Risk-Sensitive Equilibrium Concepts

• Mickey Brautbar
• Michael Kearns
• Umar Syed

We consider risk-sensitive generalizations of Nash and correlated equilibria in noncooperative games. We prove that, except for a class of degenerate games, unless a two-player game has a pure Nash equilibrium, it does not have a risksensitive Nash equilibrium. We also show that every game has a risk-sensitive correlated equilibrium. The striking contrast between these existence results is due to the different sources of randomization in Nash (private randomization) and correlated equilibria (third-party randomization).

NeurIPS Conference 2010 Conference Paper

Semi-Supervised Learning with Adversarially Missing Label Information

• Umar Syed
• Ben Taskar

We address the problem of semi-supervised learning in an adversarial setting. Instead of assuming that labels are missing at random, we analyze a less favorable scenario where the label information can be missing partially and arbitrarily, which is motivated by several practical examples. We present nearly matching upper and lower generalization bounds for learning in this setting under reasonable assumptions about available label information. Motivated by the analysis, we formulate a convex optimization problem for parameter estimation, derive an efficient algorithm, and analyze its convergence. We provide experimental results on several standard data sets showing the robustness of our algorithm to the pattern of missing label information, outperforming several strong baselines.

NeurIPS Conference 2009 Conference Paper

Adapting to the Shifting Intent of Search Queries

• Umar Syed
• Aleksandrs Slivkins
• Nina Mishra

Search engines today present results that are often oblivious to recent shifts in intent. For example, the meaning of the query independence day shifts in early July to a US holiday and to a movie around the time of the box office release. While no studies exactly quantify the magnitude of intent-shifting traffic, studies suggest that news events, seasonal topics, pop culture, etc account for 1/2 the search queries. This paper shows that the signals a search engine receives can be used to both determine that a shift in intent happened, as well as find a result that is now more relevant. We present a meta-algorithm that marries a classifier with a bandit algorithm to achieve regret that depends logarithmically on the number of query impressions, under certain assumptions. We provide strong evidence that this regret is close to the best achievable. Finally, via a series of experiments, we demonstrate that our algorithm outperforms prior approaches, particularly as the amount of intent-shifting traffic increases.

ICML Conference 2008 Conference Paper

Apprenticeship learning using linear programming

• Umar Syed
• Michael H. Bowling
• Robert E. Schapire

In apprenticeship learning, the goal is to learn a policy in a Markov decision process that is at least as good as a policy demonstrated by an expert. The difficulty arises in that the MDP's true reward function is assumed to be unknown. We show how to frame apprenticeship learning as a linear programming problem, and show that using an off-the-shelf LP solver to solve this problem results in a substantial improvement in running time over existing methods---up to two orders of magnitude faster in our experiments. Additionally, our approach produces stationary policies, while all existing methods for apprenticeship learning output policies that are "mixed", i.e. randomized combinations of stationary policies. The technique used is general enough to convert any mixed policy to a stationary policy.

NeurIPS Conference 2007 Conference Paper

A Game-Theoretic Approach to Apprenticeship Learning

• Umar Syed
• Robert Schapire

We study the problem of an apprentice learning to behave in an environment with an unknown reward function by observing the behavior of an expert. We follow on the work of Abbeel and Ng [1] who considered a framework in which the true reward function is assumed to be a linear combination of a set of known and observable features. We give a new algorithm that, like theirs, is guaranteed to learn a policy that is nearly as good as the expert's, given enough examples. However, unlike their algorithm, we show that ours may produce a policy that is substantially better than the expert's. Moreover, our algorithm is computationally faster, is easier to implement, and can be applied even in the absence of an expert. The method is based on a game-theoretic view of the problem, which leads naturally to a direct application of the multiplicative-weights algorithm of Freund and Schapire [2] for playing repeated matrix games. In addition to our formal presentation and analysis of the new algorithm, we sketch how the method can be applied when the transition function itself is unknown, and we provide an experimental demonstration of the algorithm on a toy video-game environment.

UAI Conference 2007 Conference Paper

Imitation Learning with a Value-Based Prior

• Umar Syed
• Robert E. Schapire

The goal of imitation learning is for an apprentice to learn how to behave in a stochastic environment by observing a mentor demonstrating the correct behavior. Accurate prior knowledge about the correct behavior can reduce the need for demonstrations from the mentor. We present a novel approach to encoding prior knowledge about the correct behavior, where we assume that this prior knowledge takes the form of a Markov Decision Process (MDP) that is used by the apprentice as a rough and imperfect model of the mentor's behavior. Specifically, taking a Bayesian approach, we treat the value of a policy in this modeling MDP as the log prior probability of the policy. In other words, we assume a priori that the mentor's behavior is likely to be a high value policy in the modeling MDP, though quite possibly different from the optimal policy. We describe an efficient algorithm that, given a modeling MDP and a set of demonstrations by a mentor, provably converges to a stationary point of the log posterior of the mentor's policy, where the posterior is computed with respect to the "value based" prior. We also present empirical evidence that this prior does in fact speed learning of the mentor's policy, and is an improvement in our experiments over similar previous methods.