← Authors

Akshay Krishnamurthy

83 papers · 2011–2025 · 7 conferences · across top CS/AI conferences

Achievements

πŸ—ΊοΈ Taxonomy Completionist (33) 🐝 Cross-Pollinator (10) πŸƒ Academic Marathon (14) 🌍 Conference Polyglot (7) 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌟 Keyword Trendsetter Combo (3) 🏠 Conference Loyalist (25) πŸ‘‘ Triple Crown 🌱 Topic Pioneer πŸ”¬ Deep Specialist (25) πŸ† Keyword Champion (19) 🀝 Dynamic Duo (19) ❓ The Questioner (2) πŸ—ƒοΈ Keyword Collector (93) πŸ“ˆ Trend Setter πŸš€ Conference Pioneer πŸ’Ž Century Club (83) ⚑ Prolific Year (6) πŸ”₯ Unstoppable (13)

Conferences

NIPS (25) ICML (22) ICLR (12) COLT (11) AISTATS (5) JMLR (5) ALT (3)

Top co-authors

John Langford (19) Alekh Agarwal (16) Dylan J Foster (15) Cyril Zhang (9) Sham Kakade (8) Nan Jiang (8) Wen Sun (7) Surbhi Goel (6) Dipendra Misra (6) Max Simchowitz (6)

Research topics

Methods (1) Statistics (1)

Keywords

contextual bandit (19) regret bound (14) sample complexity (11) reinforcement learning (10) representation learning (6) active learning (5) online learning (5) function approximation (4) model selection (4) sample-efficient learning (3) reward-free exploration (3) continuous action (3) contrastive learning (3) online algorithm (3) learning theory (3) distribution shift (3) off-policy evaluation (3) policy learning (2) markov decision process (2) statistical learning (2)

Papers

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