| 2026 | COLT | Characterizing Online and Private Learnability under Distributional Constraints via Generalized Smoothness. | Mose Blanchard, Abhishek Shetty, Alexander Rakhlin |
| 2026 | COLT | High-Accuracy Log-Concave Sampling with Stochastic Queries. | Fan Chen, Sinho Chewi, Constantinos Daskalakis, Alexander Rakhlin |
| 2026 | COLT | Self-Normalized Martingales and Uniform Regret Bounds for Linear Regression. | Fan Chen, Jian Qian, Alexander Rakhlin, Nikita Zhivotovskiy |
| 2026 | COLT | The Sample Complexity of Multiclass and Sparse Contextual Bandits. | Liad Erez, Fan Chen, Alon Cohen, Tomer Koren, Yishay Mansour, Shay Moran, Alexander Rakhlin |
| 2026 | COLT | Learning with Simulators: No Regret in a Computationally Bounded World. | Sasha Voitovych, Abhishek Shetty, Noah Golowich, Alexander Rakhlin |
| 2025 | COLT | Decision Making in Changing Environments: Robustness, Query-Based Learning, and Differential Privacy. | Fan Chen, Alexander Rakhlin |
| 2025 | COLT | On the Minimax Regret of Sequential Probability Assignment via Square-Root Entropy. | Zeyu Jia, Alexander Rakhlin, Yury Polyanskiy |
| 2025 | ICLR | Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF. | Tengyang Xie, Dylan J. Foster, Akshay Krishnamurthy, Corby Rosset, Ahmed Hassan Awadallah, Alexander Rakhlin |
| 2025 | ICML | GaussMark: A Practical Approach for Structural Watermarking of Language Models. | Adam Block, Alexander Rakhlin, Ayush Sekhari |
| 2025 | ICML | Do We Need to Verify Step by Step? Rethinking Process Supervision from a Theoretical Perspective. | Zeyu Jia, Alexander Rakhlin, Tengyang Xie |
| 2024 | COLING | How Far Is Too Far? Studying the Effects of Domain Discrepancy on Masked Language Models. | Subhradeep Kayal, Alexander Rakhlin, Ali Dashti, Serguei Stepaniants |
| 2024 | COLT | On the Performance of Empirical Risk Minimization with Smoothed Data. | Adam Block, Alexander Rakhlin, Abhishek Shetty |
| 2024 | COLT | Near-Optimal Learning and Planning in Separated Latent MDPs. | Fan Chen, Constantinos Daskalakis, Noah Golowich, Alexander Rakhlin |
| 2024 | COLT | Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data. | Zeyu Jia, Alexander Rakhlin, Ayush Sekhari, Chen-Yu Wei |
| 2024 | ICML | The Non-linear F-Design and Applications to Interactive Learning. | Alekh Agarwal, Jian Qian, Alexander Rakhlin, Tong Zhang |
| 2024 | ICML | Random Latent Exploration for Deep Reinforcement Learning. | Srinath Mahankali, Zhang-Wei Hong, Ayush Sekhari, Alexander Rakhlin, Pulkit Agrawal |
| 2023 | COLT | Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making. | Adam Block, Max Simchowitz, Alexander Rakhlin |
| 2023 | COLT | On the Complexity of Multi-Agent Decision Making: From Learning in Games to Partial Monitoring. | Dean P. Foster, Dylan J. Foster, Noah Golowich, Alexander Rakhlin |
| 2023 | ICML | Representation Learning with Multi-Step Inverse Kinematics: An Efficient and Optimal Approach to Rich-Observation RL. | Zakaria Mhammedi, Dylan J. Foster, Alexander Rakhlin |
| 2022 | COLT | Smoothed Online Learning is as Easy as Statistical Learning. | Adam Block, Yuval Dagan, Noah Golowich, Alexander Rakhlin |
| 2022 | COLT | Damped Online Newton Step for Portfolio Selection. | Zakaria Mhammedi, Alexander Rakhlin |
| 2021 | COLT | Majorizing Measures, Sequential Complexities, and Online Learning. | Adam Block, Yuval Dagan, Alexander Rakhlin |
| 2021 | COLT | Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective. | Dylan J. Foster, Alexander Rakhlin, David Simchi-Levi, Yunzong Xu |
| 2021 | COLT | On the Minimal Error of Empirical Risk Minimization. | Gil Kur, Alexander Rakhlin |
| 2021 | ICML | Top-k eXtreme Contextual Bandits with Arm Hierarchy. | Rajat Sen, Alexander Rakhlin, Lexing Ying, Rahul Kidambi, Dean P. Foster, Daniel N. Hill, Inderjit S. Dhillon |
| 2020 | COLT | On Suboptimality of Least Squares with Application to Estimation of Convex Bodies. | Gil Kur, Alexander Rakhlin, Adityanand Guntuboyina |
| 2020 | COLT | On the Multiple Descent of Minimum-Norm Interpolants and Restricted Lower Isometry of Kernels. | Tengyuan Liang, Alexander Rakhlin, Xiyu Zhai |
| 2020 | ICML | Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles. | Dylan J. Foster, Alexander Rakhlin |
| 2019 | AISTATS | Does data interpolation contradict statistical optimality? | Mikhail Belkin, Alexander Rakhlin, Alexandre B. Tsybakov |
| 2019 | AISTATS | Fisher-Rao Metric, Geometry, and Complexity of Neural Networks. | Tengyuan Liang, Tomaso A. Poggio, Alexander Rakhlin, James Stokes |
| 2019 | COLT | Consistency of Interpolation with Laplace Kernels is a High-Dimensional Phenomenon. | Alexander Rakhlin, Xiyu Zhai |
| 2019 | ICML | Near optimal finite time identification of arbitrary linear dynamical systems. | Tuhin Sarkar, Alexander Rakhlin |
| 2018 | COLT | Online Learning: Sufficient Statistics and the Burkholder Method. | Dylan J. Foster, Alexander Rakhlin, Karthik Sridharan |
| 2018 | COLT | Size-Independent Sample Complexity of Neural Networks. | Noah Golowich, Alexander Rakhlin, Ohad Shamir |
| 2018 | CVPR | Land Cover Classification From Satellite Imagery With U-Net and Lovasz-Softmax Loss. | Alexander Rakhlin, Alex Davydow, Sergey I. Nikolenko |
| 2018 | ICMLA | Angiodysplasia Detection and Localization Using Deep Convolutional Neural Networks. | Alexey A. Shvets, Vladimir I. Iglovikov, Alexander Rakhlin, Alexandr A. Kalinin |
| 2018 | ICMLA | Automatic Instrument Segmentation in Robot-Assisted Surgery using Deep Learning. | Alexey A. Shvets, Alexander Rakhlin, Alexandr A. Kalinin, Vladimir I. Iglovikov |
| 2018 | MICCAI | Paediatric Bone Age Assessment Using Deep Convolutional Neural Networks. | Vladimir I. Iglovikov, Alexander Rakhlin, Alexandr A. Kalinin, Alexey A. Shvets |
| 2017 | AISTATS | Efficient Online Multiclass Prediction on Graphs via Surrogate Losses. | Alexander Rakhlin, Karthik Sridharan |
| 2017 | COLT | ZigZag: A New Approach to Adaptive Online Learning. | Dylan J. Foster, Alexander Rakhlin, Karthik Sridharan |
| 2017 | COLT | Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis. | Maxim Raginsky, Alexander Rakhlin, Matus Telgarsky |
| 2017 | COLT | On Equivalence of Martingale Tail Bounds and Deterministic Regret Inequalities. | Alexander Rakhlin, Karthik Sridharan |
| 2017 | ICASSP | Multi-armed bandits in multi-agent networks. | Shahin Shahrampour, Alexander Rakhlin, Ali Jadbabaie |
| 2016 | COLT | Conference on Learning Theory 2016: Preface. | Vitaly Feldman, Alexander Rakhlin |
| 2016 | ICML | BISTRO: An Efficient Relaxation-Based Method for Contextual Bandits. | Alexander Rakhlin, Karthik Sridharan |
| 2016 | ITW | Information-theoretic analysis of stability and bias of learning algorithms. | Maxim Raginsky, Alexander Rakhlin, Matthew Tsao, Yihong Wu, Aolin Xu |
| 2015 | AISTATS | Online Optimization : Competing with Dynamic Comparators. | Ali Jadbabaie, Alexander Rakhlin, Shahin Shahrampour, Karthik Sridharan |
| 2015 | COLT | Escaping the Local Minima via Simulated Annealing: Optimization of Approximately Convex Functions. | Alexandre Belloni, Tengyuan Liang, Hariharan Narayanan, Alexander Rakhlin |
| 2015 | COLT | Learning with Square Loss: Localization through Offset Rademacher Complexity. | Tengyuan Liang, Alexander Rakhlin, Karthik Sridharan |
| 2015 | COLT | Hierarchies of Relaxations for Online Prediction Problems with Evolving Constraints. | Alexander Rakhlin, Karthik Sridharan |
| 2014 | COLT | Online Non-Parametric Regression. | Alexander Rakhlin, Karthik Sridharan |
| 2013 | AISTATS | Localization and Adaptation in Online Learning. | Alexander Rakhlin, Ohad Shamir, Karthik Sridharan |
| 2013 | COLT | Competing With Strategies. | Wei Han, Alexander Rakhlin, Karthik Sridharan |
| 2013 | COLT | Online Learning with Predictable Sequences. | Alexander Rakhlin, Karthik Sridharan |
| 2013 | ITW | On Semi-Probabilistic universal prediction. | Alexander Rakhlin, Karthik Sridharan |
| 2012 | ICML | Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization. | Alexander Rakhlin, Ohad Shamir, Karthik Sridharan |
| 2009 | COLT | A Stochastic View of Optimal Regret through Minimax Duality. | Jacob D. Abernethy, Alekh Agarwal, Peter L. Bartlett, Alexander Rakhlin |
| 2009 | COLT | Beating the Adaptive Bandit with High Probability. | Jacob D. Abernethy, Alexander Rakhlin |
| 2009 | COLT | An Efficient Bandit Algorithm for sqrt(T) Regret in Online Multiclass Prediction?. | Jacob D. Abernethy, Alexander Rakhlin |
| 2008 | COLT | Optimal Stragies and Minimax Lower Bounds for Online Convex Games. | Jacob D. Abernethy, Peter L. Bartlett, Alexander Rakhlin, Ambuj Tewari |
| 2008 | COLT | Competing in the Dark: An Efficient Algorithm for Bandit Linear Optimization. | Jacob D. Abernethy, Elad Hazan, Alexander Rakhlin |
| 2008 | COLT | High-Probability Regret Bounds for Bandit Online Linear Optimization. | Peter L. Bartlett, Varsha Dani, Thomas P. Hayes, Sham M. Kakade, Alexander Rakhlin, Ambuj Tewari |
| 2008 | ICCAD | Game-theoretic timing analysis. | Sanjit A. Seshia, Alexander Rakhlin |
| 2007 | COLT | Multitask Learning with Expert Advice. | Jacob D. Abernethy, Peter L. Bartlett, Alexander Rakhlin |
| 2007 | ICML | Online discovery of similarity mappings. | Alexander Rakhlin, Jacob D. Abernethy, Peter L. Bartlett |