Mehryar Mohri

Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization COLT 2026 Efficient Opportunistic Approachability ALT 2026 Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data ICML 2025 Enhanced H-Consistency Bounds ALT 2025 Mastering Multiple-Expert Routing: Realizable H-Consistency and Strong Guarantees for Learning to Defer ICML 2025 Principled Algorithms for Optimizing Generalized Metrics in Binary Classification ICML 2025 Rate-Preserving Reductions for Blackwell Approachability COLT 2025 H-Consistency Guarantees for Regression ICML 2024 A Universal Growth Rate for Learning with Smooth Surrogate Losses NeurIPS 2024 Cardinality-Aware Set Prediction and Top-k Classification NeurIPS 2024 Differentially Private Domain Adaptation with Theoretical Guarantees ICML 2024 Multi-Label Learning with Stronger Consistency Guarantees NeurIPS 2024 Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithms ALT 2024 Realizable H-Consistent and Bayes-Consistent Loss Functions for Learning to Defer NeurIPS 2024 Regression with Multi-Expert Deferral ICML 2024 Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention AISTATS 2024 H-Consistency Bounds: Characterization and Extensions NeurIPS 2023 H-Consistency Bounds for Pairwise Misranking Loss Surrogates ICML 2023 Cross-Entropy Loss Functions: Theoretical Analysis and Applications ICML 2023 Principled Approaches for Private Adaptation from a Public Source AISTATS 2023 Pseudonorm Approachability and Applications to Regret Minimization ALT 2023 Reinforcement Learning Can Be More Efficient with Multiple Rewards ICML 2023 Structured Prediction with Stronger Consistency Guarantees NeurIPS 2023 Theoretically Grounded Loss Functions and Algorithms for Adversarial Robustness AISTATS 2023 Two-Stage Learning to Defer with Multiple Experts NeurIPS 2023 Differentially Private Learning with Margin Guarantees NeurIPS 2022 Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation ICML 2022 H-Consistency Bounds for Surrogate Loss Minimizers ICML 2022 Multi-Class H-Consistency Bounds NeurIPS 2022 Open Problem: Better Differentially Private Learning Algorithms with Margin Guarantees COLT 2022 Open Problem: Finite-Time Instance Dependent Optimality for Stochastic Online Learning with Feedback Graphs COLT 2022 Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality NeurIPS 2022 Strategizing against Learners in Bayesian Games COLT 2022 A Discriminative Technique for Multiple-Source Adaptation ICML 2021 Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations NeurIPS 2021 A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning NeurIPS 2021 A Theory of Multiple-Source Adaptation with Limited Target Labeled Data AISTATS 2021 Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning NeurIPS 2021 Boosting with Multiple Sources NeurIPS 2021 Breaking the centralized barrier for cross-device federated learning NeurIPS 2021 Calibration and Consistency of Adversarial Surrogate Losses NeurIPS 2021 Communication-Efficient Agnostic Federated Averaging Interspeech 2021 Corralling Stochastic Bandit Algorithms AISTATS 2021 Learning with User-Level Privacy NeurIPS 2021 On the Existence of The Adversarial Bayes Classifier NeurIPS 2021 Relative Deviation Margin Bounds ICML 2021 Adapting to Misspecification in Contextual Bandits NeurIPS 2020 Adaptive Region-Based Active Learning ICML 2020 Adversarial Learning Guarantees for Linear Hypotheses and Neural Networks ICML 2020 Agnostic Learning with Multiple Objectives NeurIPS 2020 FedBoost: A Communication-Efficient Algorithm for Federated Learning ICML 2020 Online Learning with Dependent Stochastic Feedback Graphs ICML 2020 PAC-Bayes Learning Bounds for Sample-Dependent Priors NeurIPS 2020 Reinforcement Learning with Feedback Graphs NeurIPS 2020 SCAFFOLD: Stochastic Controlled Averaging for Federated Learning ICML 2020 Active Learning with Disagreement Graphs ICML 2019 Adaptation Based on Generalized Discrepancy JMLR 2019 Agnostic Federated Learning ICML 2019 Bandits with Feedback Graphs and Switching Costs NeurIPS 2019 Hypothesis Set Stability and Generalization NeurIPS 2019 Learning GANs and Ensembles Using Discrepancy NeurIPS 2019 Online Learning with Sleeping Experts and Feedback Graphs ICML 2019 Online Non-Additive Path Learning under Full and Partial Information ALT 2019 Region-Based Active Learning AISTATS 2019 Regularized Gradient Boosting NeurIPS 2019 Algorithmic Learning Theory ALT 2018: Preface ALT 2018 Algorithms and Theory for Multiple-Source Adaptation NeurIPS 2018 Competing with Automata-based Expert Sequences AISTATS 2018 Efficient Gradient Computation for Structured Output Learning with Rational and Tropical Losses NeurIPS 2018 Logistic Regression: The Importance of Being Improper COLT 2018 Online Learning with Abstention ICML 2018 Policy Regret in Repeated Games NeurIPS 2018 AdaNet: Adaptive Structural Learning of Artificial Neural Networks ICML 2017 Discriminative State Space Models NeurIPS 2017 Online Learning with Transductive Regret NeurIPS 2017 Parameter-Free Online Learning via Model Selection NeurIPS 2017 Accelerating Online Convex Optimization via Adaptive Prediction AISTATS 2016 Boosting with Abstention NeurIPS 2016 Learning Algorithms for Second-Price Auctions with Reserve JMLR 2016 Learning N-Gram Language Models from Uncertain Data Interspeech 2016 Optimistic Bandit Convex Optimization NeurIPS 2016 Structured Prediction Theory Based on Factor Graph Complexity NeurIPS 2016 Time series prediction and online learning COLT 2016 Learning Theory and Algorithms for Forecasting Non-stationary Time Series NeurIPS 2015 On-Line Learning Algorithms for Path Experts with Non-Additive Losses COLT 2015 Revenue Optimization against Strategic Buyers NeurIPS 2015 Structural Maxent Models ICML 2015 Conditional Swap Regret and Conditional Correlated Equilibrium NeurIPS 2014 Deep Boosting ICML 2014 Ensemble Methods for Structured Prediction ICML 2014 Learning Ensembles of Structured Prediction Rules ACL 2014 Learning Theory and Algorithms for revenue optimization in second price auctions with reserve ICML 2014 Multi-Class Deep Boosting NeurIPS 2014 Optimal Regret Minimization in Posted-Price Auctions with Strategic Buyers NeurIPS 2014 Large-scale SVD and Manifold Learning JMLR 2013 Learning Kernels Using Local Rademacher Complexity NeurIPS 2013 Multi-Class Classification with Maximum Margin Multiple Kernel ICML 2013 Accuracy at the Top NeurIPS 2012 Algorithms for Learning Kernels Based on Centered Alignment JMLR 2012 Sampling Methods for the Nyström Method JMLR 2012 Spectral Learning of General Weighted Automata via Constrained Matrix Completion NeurIPS 2012 Can matrix coherence be efficiently and accurately estimated? AISTATS 2011 Discriminative Topic Segmentation of Text and Speech AISTATS 2010 Expected Sequence Similarity Maximization NAACL 2010 Half Transductive Ranking AISTATS 2010 Learning Bounds for Importance Weighting NeurIPS 2010 On the Impact of Kernel Approximation on Learning Accuracy AISTATS 2010 Stability Bounds for Stationary φ-mixing and β-mixing Processes JMLR 2010 Efficient Large-Scale Distributed Training of Conditional Maximum Entropy Models NeurIPS 2009 Ensemble Nystrom Method NeurIPS 2009 Learning Non-Linear Combinations of Kernels NeurIPS 2009 Polynomial Semantic Indexing NeurIPS 2009 Domain Adaptation with Multiple Sources NeurIPS 2008 Rademacher Complexity Bounds for Non-I.I.D. Processes NeurIPS 2008 Stability Bounds for Non-i.i.d. Processes NeurIPS 2007 On Transductive Regression NeurIPS 2006 Probabilistic Context-Free Grammar Induction Based on Structural Zeros NAACL 2006 Gaussian Margin Machines AISTATS 2005 Sampling Techniques for the Nystrom Method AISTATS 2005 Rational Kernels: Theory and Algorithms JMLR 2004 Statistical Modeling for Unit Selection in Speech Synthesis ACL 2004 Generalized Algorithms for Constructing Statistical Language Models ACL 2003