Akshay Krishnamurthy

Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum COLT 2026 Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics ICLR 2025 Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification (extended abstract) COLT 2025 Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization ICLR 2025 Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF ICLR 2025 Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment ICML 2025 Self-Improvement in Language Models: The Sharpening Mechanism ICLR 2025 The Role of Environment Access in Agnostic Reinforcement Learning (Extended Abstract) COLT 2025 Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression ICLR 2024 Can large language models explore in-context? NeurIPS 2024 Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning COLT 2024 Model-Free Representation Learning and Exploration in Low-Rank MDPs JMLR 2024 Oracle-Efficient Pessimism: Offline Policy Optimization In Contextual Bandits AISTATS 2024 Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity NeurIPS 2024 Rich-Observation Reinforcement Learning with Continuous Latent Dynamics ICML 2024 Scalable Online Exploration via Coverability ICML 2024 A Complete Characterization of Linear Estimators for Offline Policy Evaluation JMLR 2023 Exposing Attention Glitches with Flip-Flop Language Modeling NeurIPS 2023 Hybrid RL: Using both offline and online data can make RL efficient ICLR 2023 Learning Hidden Markov Models Using Conditional Samples COLT 2023 Statistical Learning under Heterogeneous Distribution Shift ICML 2023 Streaming Active Learning with Deep Neural Networks ICML 2023 Transformers Learn Shortcuts to Automata ICLR 2023 Anti-Concentrated Confidence Bonuses For Scalable Exploration ICLR 2022 Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability ALT 2022 Investigating the Role of Negatives in Contrastive Representation Learning AISTATS 2022 Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation COLT 2022 On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL NeurIPS 2022 Provable Reinforcement Learning with a Short-Term Memory ICML 2022 Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics ICLR 2022 Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information COLT 2022 Sparsity in Partially Controllable Linear Systems ICML 2022 Understanding Contrastive Learning Requires Incorporating Inductive Biases ICML 2022 Universal and data-adaptive algorithms for model selection in linear contextual bandits ICML 2022 Bayesian decision-making under misspecified priors with applications to meta-learning NeurIPS 2021 Contrastive Estimation Reveals Topic Posterior Information to Linear Models JMLR 2021 Contrastive learning, multi-view redundancy, and linear models ALT 2021 Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination NeurIPS 2021 Gone Fishing: Neural Active Learning with Fisher Embeddings NeurIPS 2021 Optimism in Reinforcement Learning with Generalized Linear Function Approximation ICLR 2021 Adaptive Estimator Selection for Off-Policy Evaluation ICML 2020 Algebraic and Analytic Approaches for Parameter Learning in Mixture Models ALT 2020 Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting JMLR 2020 Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds ICLR 2020 Doubly robust off-policy evaluation with shrinkage ICML 2020 Efficient Contextual Bandits with Continuous Actions NeurIPS 2020 FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs NeurIPS 2020 Information Theoretic Regret Bounds for Online Nonlinear Control NeurIPS 2020 Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning ICML 2020 Learning the Linear Quadratic Regulator from Nonlinear Observations NeurIPS 2020 Open Problem: Model Selection for Contextual Bandits COLT 2020 Private Reinforcement Learning with PAC and Regret Guarantees ICML 2020 Provably adaptive reinforcement learning in metric spaces NeurIPS 2020 Reward-Free Exploration for Reinforcement Learning ICML 2020 Sample-Efficient Reinforcement Learning of Undercomplete POMDPs NeurIPS 2020 Active Learning for Cost-Sensitive Classification JMLR 2019 Contextual bandits with continuous actions: Smoothing, zooming, and adapting COLT 2019 Disagreement-Based Combinatorial Pure Exploration: Sample Complexity Bounds and an Efficient Algorithm COLT 2019 Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches COLT 2019 Model Selection for Contextual Bandits NeurIPS 2019 Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments ICML 2019 Provably efficient RL with Rich Observations via Latent State Decoding ICML 2019 Sample Complexity of Learning Mixture of Sparse Linear Regressions NeurIPS 2019 Contextual bandits with surrogate losses: Margin bounds and efficient algorithms NeurIPS 2018 Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning ICLR 2018 On Oracle-Efficient PAC RL with Rich Observations NeurIPS 2018 Parallelised Bayesian Optimisation via Thompson Sampling AISTATS 2018 Semiparametric Contextual Bandits ICML 2018 Active Learning for Cost-Sensitive Classification ICML 2017 Contextual Decision Processes with low Bellman rank are PAC-Learnable ICML 2017 Off-policy evaluation for slate recommendation NeurIPS 2017 Open Problem: First-Order Regret Bounds for Contextual Bandits COLT 2017 Contextual semibandits via supervised learning oracles NeurIPS 2016 Efficient Algorithms for Adversarial Contextual Learning ICML 2016 Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits NeurIPS 2016 PAC Reinforcement Learning with Rich Observations NeurIPS 2016 Learning to Search Better than Your Teacher ICML 2015 Nonparametric von Mises Estimators for Entropies, Divergences and Mutual Informations NeurIPS 2015 On Estimating L_2^2 Divergence AISTATS 2015 Nonparametric Estimation of Renyi Divergence and Friends ICML 2014 Detecting Activations over Graphs using Spanning Tree Wavelet Bases AISTATS 2013 Low-Rank Matrix and Tensor Completion via Adaptive Sampling NeurIPS 2013 Near-optimal Anomaly Detection in Graphs using Lovasz Extended Scan Statistic NeurIPS 2013 Noise Thresholds for Spectral Clustering NeurIPS 2011