| 2026 | COLT | Adaptive Matrix Online Learning through Smoothing with Guarantees for Nonsmooth Nonconvex Optimization. | Ruichen Jiang, Zakaria Mhammedi, Mehryar Mohri, Aryan Mokhtari |
| 2025 | ALT | Enhanced H-Consistency Bounds. | Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 2025 | COLT | Rate-Preserving Reductions for Blackwell Approachability. | Christoph Dann, Yishay Mansour, Mehryar Mohri, Jon Schneider, Balasubramanian Sivan |
| 2025 | ICML | Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data. | Corinna Cortes, Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 2025 | ICML | Mastering Multiple-Expert Routing: Realizable H-Consistency and Strong Guarantees for Learning to Defer. | Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 2025 | ICML | Principled Algorithms for Optimizing Generalized Metrics in Binary Classification. | Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 2024 | AISTATS | Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention. | Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 2024 | ALT | Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithms. | Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 2024 | ICML | Differentially Private Domain Adaptation with Theoretical Guarantees. | Raef Bassily, Corinna Cortes, Anqi Mao, Mehryar Mohri |
| 2024 | ICML | Regression with Multi-Expert Deferral. | Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 2024 | ICML | H-Consistency Guarantees for Regression. | Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 2024 | ISAIM | A Theory of Learning with Competing Objectives and User Feedback. | Pranjal Awasthi, Corinna Cortes, Yishay Mansour, Mehryar Mohri |
| 2024 | ISAIM | Principled Approaches for Learning to Defer with Multiple Experts. | Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 2023 | AISTATS | Theoretically Grounded Loss Functions and Algorithms for Adversarial Robustness. | Pranjal Awasthi, Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 2023 | AISTATS | Principled Approaches for Private Adaptation from a Public Source. | Raef Bassily, Mehryar Mohri, Ananda Theertha Suresh |
| 2023 | ALT | Pseudonorm Approachability and Applications to Regret Minimization. | Christoph Dann, Yishay Mansour, Mehryar Mohri, Jon Schneider, Balasubramanian Sivan |
| 2023 | ICML | Reinforcement Learning Can Be More Efficient with Multiple Rewards. | Christoph Dann, Yishay Mansour, Mehryar Mohri |
| 2023 | ICML | H-Consistency Bounds for Pairwise Misranking Loss Surrogates. | Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 2023 | ICML | Cross-Entropy Loss Functions: Theoretical Analysis and Applications. | Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 2022 | COLT | Strategizing against Learners in Bayesian Games. | Yishay Mansour, Mehryar Mohri, Jon Schneider, Balasubramanian Sivan |
| 2022 | ICML | H-Consistency Bounds for Surrogate Loss Minimizers. | Pranjal Awasthi, Anqi Mao, Mehryar Mohri, Yutao Zhong |
| 2022 | ICML | Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation. | Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan |
| 2021 | AISTATS | Corralling Stochastic Bandit Algorithms. | Raman Arora, Teodor Vanislavov Marinov, Mehryar Mohri |
| 2021 | AISTATS | A Theory of Multiple-Source Adaptation with Limited Target Labeled Data. | Yishay Mansour, Mehryar Mohri, Jae Ro, Ananda Theertha Suresh, Ke Wu |
| 2021 | ICML | Relative Deviation Margin Bounds. | Corinna Cortes, Mehryar Mohri, Ananda Theertha Suresh |
| 2021 | ICML | A Discriminative Technique for Multiple-Source Adaptation. | Corinna Cortes, Mehryar Mohri, Ananda Theertha Suresh, Ningshan Zhang |
| 2021 | Interspeech | Communication-Efficient Agnostic Federated Averaging. | Jae Ro, Mingqing Chen, Rajiv Mathews, Mehryar Mohri, Ananda Theertha Suresh |
| 2020 | ICML | Adversarial Learning Guarantees for Linear Hypotheses and Neural Networks. | Pranjal Awasthi, Natalie Frank, Mehryar Mohri |
| 2020 | ICML | Adaptive Region-Based Active Learning. | Corinna Cortes, Giulia DeSalvo, Claudio Gentile, Mehryar Mohri, Ningshan Zhang |
| 2020 | ICML | Online Learning with Dependent Stochastic Feedback Graphs. | Corinna Cortes, Giulia DeSalvo, Claudio Gentile, Mehryar Mohri, Ningshan Zhang |
| 2020 | ICML | FedBoost: A Communication-Efficient Algorithm for Federated Learning. | Jenny Hamer, Mehryar Mohri, Ananda Theertha Suresh |
| 2020 | ICML | SCAFFOLD: Stochastic Controlled Averaging for Federated Learning. | Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank J. Reddi, Sebastian U. Stich, Ananda Theertha Suresh |
| 2019 | AISTATS | Region-Based Active Learning. | Corinna Cortes, Giulia DeSalvo, Claudio Gentile, Mehryar Mohri, Ningshan Zhang |
| 2019 | ALT | Online Non-Additive Path Learning under Full and Partial Information. | Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Holakou Rahmanian, Manfred K. Warmuth |
| 2019 | ICML | Online Learning with Sleeping Experts and Feedback Graphs. | Corinna Cortes, Giulia DeSalvo, Claudio Gentile, Mehryar Mohri, Scott Yang |
| 2019 | ICML | Active Learning with Disagreement Graphs. | Corinna Cortes, Giulia DeSalvo, Mehryar Mohri, Ningshan Zhang, Claudio Gentile |
| 2019 | ICML | Agnostic Federated Learning. | Mehryar Mohri, Gary Sivek, Ananda Theertha Suresh |
| 2018 | AISTATS | Competing with Automata-based Expert Sequences. | Mehryar Mohri, Scott Yang |
| 2018 | COLT | Logistic Regression: The Importance of Being Improper. | Dylan J. Foster, Satyen Kale, Haipeng Luo, Mehryar Mohri, Karthik Sridharan |
| 2018 | ICML | Online Learning with Abstention. | Corinna Cortes, Giulia DeSalvo, Claudio Gentile, Mehryar Mohri, Scott Yang |
| 2017 | ICML | AdaNet: Adaptive Structural Learning of Artificial Neural Networks. | Corinna Cortes, Xavier Gonzalvo, Vitaly Kuznetsov, Mehryar Mohri, Scott Yang |
| 2016 | AAAI | Random Composite Forests. | Giulia DeSalvo, Mehryar Mohri |
| 2016 | AISTATS | Accelerating Online Convex Optimization via Adaptive Prediction. | Mehryar Mohri, Scott Yang |
| 2016 | ALT | Learning with Rejection. | Corinna Cortes, Giulia DeSalvo, Mehryar Mohri |
| 2016 | ALT | Structural Online Learning. | Mehryar Mohri, Scott Yang |
| 2016 | COLT | Time series prediction and online learning. | Vitaly Kuznetsov, Mehryar Mohri |
| 2016 | Interspeech | Learning N-Gram Language Models from Uncertain Data. | Vitaly Kuznetsov, Hank Liao, Mehryar Mohri, Michael Riley, Brian Roark |
| 2016 | UAI | Adaptive Algorithms and Data-Dependent Guarantees for Bandit Convex Optimization. | Scott Yang, Mehryar Mohri |
| 2015 | ALT | On the Rademacher Complexity of Weighted Automata. | Borja Balle, Mehryar Mohri |
| 2015 | ALT | Learning with Deep Cascades. | Giulia DeSalvo, Mehryar Mohri, Umar Syed |
| 2015 | COLT | On-Line Learning Algorithms for Path Experts with Non-Additive Losses. | Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Manfred K. Warmuth |
| 2015 | ICML | Structural Maxent Models. | Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri, Umar Syed |
| 2015 | ISIT | Automata and graph compression. | Mehryar Mohri, Michael Riley, Ananda Theertha Suresh |
| 2015 | KDD | Adaptation Algorithm and Theory Based on Generalized Discrepancy. | Corinna Cortes, Mehryar Mohri, Andres Muoz Medina |
| 2015 | UAI | Non-parametric Revenue Optimization for Generalized Second Price auctions.. | Mehryar Mohri, Andres Muoz Medina |
| 2014 | ACL | Learning Ensembles of Structured Prediction Rules. | Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri |
| 2014 | ALT | Generalization Bounds for Time Series Prediction with Non-stationary Processes. | Vitaly Kuznetsov, Mehryar Mohri |
| 2014 | ICML | Ensemble Methods for Structured Prediction. | Corinna Cortes, Vitaly Kuznetsov, Mehryar Mohri |
| 2014 | ICML | Deep Boosting. | Corinna Cortes, Mehryar Mohri, Umar Syed |
| 2014 | ICML | Learning Theory and Algorithms for revenue optimization in second price auctions with reserve. | Mehryar Mohri, Andres Muoz Medina |
| 2013 | ICML | Multi-Class Classification with Maximum Margin Multiple Kernel. | Corinna Cortes, Mehryar Mohri, Afshin Rostamizadeh |
| 2012 | ALT | New Analysis and Algorithm for Learning with Drifting Distributions. | Mehryar Mohri, Andres Muoz Medina |
| 2011 | ALT | Domain Adaptation in Regression. | Corinna Cortes, Mehryar Mohri |
| 2011 | UAI | Ensembles of Kernel Predictors. | Corinna Cortes, Mehryar Mohri, Afshin Rostamizadeh |
| 2010 | ICML | Two-Stage Learning Kernel Algorithms. | Corinna Cortes, Mehryar Mohri, Afshin Rostamizadeh |
| 2010 | ICML | Generalization Bounds for Learning Kernels. | Corinna Cortes, Mehryar Mohri, Afshin Rostamizadeh |
| 2010 | NAACL | Expected Sequence Similarity Maximization. | Cyril Allauzen, Shankar Kumar, Wolfgang Macherey, Mehryar Mohri, Michael Riley |
| 2009 | COLT | Domain Adaptation: Learning Bounds and Algorithms. | Yishay Mansour, Mehryar Mohri, Afshin Rostamizadeh |
| 2009 | ICML | On sampling-based approximate spectral decomposition. | Sanjiv Kumar, Mehryar Mohri, Ameet Talwalkar |
| 2009 | Interspeech | A new quality measure for topic segmentation of text and speech. | Mehryar Mohri, Pedro J. Moreno, Eugene Weinstein |
| 2009 | UAI | L2 Regularization for Learning Kernels. | Corinna Cortes, Mehryar Mohri, Afshin Rostamizadeh |
| 2009 | UAI | Multiple Source Adaptation and the Rnyi Divergence. | Yishay Mansour, Mehryar Mohri, Afshin Rostamizadeh |
| 2008 | ALT | Sample Selection Bias Correction Theory. | Corinna Cortes, Mehryar Mohri, Michael Riley, Afshin Rostamizadeh |
| 2008 | COLT | An Efficient Reduction of Ranking to Classification. | Nir Ailon, Mehryar Mohri |
| 2008 | DLT | General Algorithms for Testing the Ambiguity of Finite Automata. | Cyril Allauzen, Mehryar Mohri, Ashish Rastogi |
| 2008 | ICML | Sequence kernels for predicting protein essentiality. | Cyril Allauzen, Mehryar Mohri, Ameet Talwalkar |
| 2008 | ICML | Stability of transductive regression algorithms. | Corinna Cortes, Mehryar Mohri, Dmitry Pechyony, Ashish Rastogi |
| 2007 | COLT | Learning Languages with Rational Kernels. | Corinna Cortes, Leonid Kontorovich, Mehryar Mohri |
| 2007 | ICML | Magnitude-preserving ranking algorithms. | Corinna Cortes, Mehryar Mohri, Ashish Rastogi |
| 2006 | ALT | Learning Linearly Separable Languages. | Leonid Kontorovich, Corinna Cortes, Mehryar Mohri |
| 2006 | LATIN | Efficient Computation of the Relative Entropy of Probabilistic Automata. | Corinna Cortes, Mehryar Mohri, Ashish Rastogi, Michael Riley |
| 2006 | MFCS | A Unified Construction of the Glushkov, Follow, and Antimirov Automata. | Cyril Allauzen, Mehryar Mohri |
| 2006 | NAACL | Probabilistic Context-Free Grammar Induction Based on Structural Zeros. | Mehryar Mohri, Brian Roark |
| 2005 | COLT | Margin-Based Ranking Meets Boosting in the Middle. | Cynthia Rudin, Corinna Cortes, Mehryar Mohri, Robert E. Schapire |
| 2005 | ICASSP | A Comparison of Classifiers for Detecting Emotion from Speech. | Izhak Shafran, Mehryar Mohri |
| 2005 | ICML | A general regression technique for learning transductions. | Corinna Cortes, Mehryar Mohri, Jason Weston |
| 2004 | ACL | Statistical Modeling for Unit Selection in Speech Synthesis. | Mehryar Mohri, Cyril Allauzen, Michael Riley |
| 2004 | ICASSP | A generalized construction of integrated speech recognition transducers. | Cyril Allauzen, Mehryar Mohri, Michael Riley, Brian Roark |
| 2004 | ICML | Distribution kernels based on moments of counts. | Corinna Cortes, Mehryar Mohri |
| 2003 | ACL | Generalized Algorithms for Constructing Statistical Language Models. | Cyril Allauzen, Mehryar Mohri, Brian Roark |
| 2003 | COLT | Positive Definite Rational Kernels. | Corinna Cortes, Patrick Haffner, Mehryar Mohri |
| 2003 | COLT | Learning from Uncertain Data. | Mehryar Mohri |
| 2003 | ICASSP | Generalized optimization algorithm for speech recognition transducers. | Cyril Allauzen, Mehryar Mohri |
| 2003 | ICASSP | Lattice kernels for spoken-dialog classification. | Corinna Cortes, Patrick Haffner, Mehryar Mohri |
| 2003 | Interspeech | Weighted automata kernels - general framework and algorithms. | Corinna Cortes, Patrick Haffner, Mehryar Mohri |
| 2002 | Interspeech | A comparison of two LVR search optimization techniques. | Stephan Kanthak, Hermann Ney, Michael Riley, Mehryar Mohri |
| 2002 | Interspeech | An efficient algorithm for the n-best-strings problem. | Mehryar Mohri, Michael Riley |
| 2001 | Interspeech | A weight pushing algorithm for large vocabulary speech recognition. | Mehryar Mohri, Michael Riley |
| 1999 | Interspeech | Rapid unit selection from a large speech corpus for concatenative speech synthesis. | Mark C. Beutnagel, Mehryar Mohri, Michael Riley |
| 1999 | Interspeech | Integrated context-dependent networks in very large vocabulary speech recognition. | Mehryar Mohri, Michael Riley |
| 1998 | ACL | Dynamic Compilation of Weighted Context-Free Grammars. | Mehryar Mohri, Fernando C. N. Pereira |
| 1998 | ICASSP | Full expansion of context-dependent networks in large vocabulary speech recognition. | Mehryar Mohri, Michael Riley, Donald Hindle, Andrej Ljolje, Fernando C. N. Pereira |
| 1998 | Interspeech | VPQ: a spoken language interface to large scale directory information. | Bruce Buntschuh, Candace A. Kamm, Giuseppe Di Fabbrizio, Alicia Abella, Mehryar Mohri, Shrikanth S. Narayanan, Ilija Zeljkovic, R. Doug Sharp, Jeremy H. Wright, S. Marcus, J. Shaffer, R. Duncan, Jay G. Wilpon |
| 1997 | Interspeech | Weighted determinization and minimization for large vocabulary speech recognition. | Mehryar Mohri, Michael Riley |
| 1997 | Interspeech | Transducer composition for context-dependent network expansion. | Michael Riley, Fernando Pereira, Mehryar Mohri |
| 1996 | ACL | An Efficient Compiler for Weighted Rewrite Rules. | Mehryar Mohri, Richard Sproat |
| 1995 | CPM | Matching Patterns of An Automaton. | Mehryar Mohri |
| 1995 | NLDB | Computation of French Temporal Expressions to Query Databases. | Denis Maurel, Mehryar Mohri |
| 1994 | ACL | Compact Representations by Finite-State Transducers. | Mehryar Mohri |
| 1994 | CPM | Minimization of Sequential Transducers. | Mehryar Mohri |