Akshay Krishnamurthy

Decision Sciences · Social Sciences

26h-index2.8kcitations150works0.32yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Bandit Algorithms Research(65), Machine Learning and Algorithms(61), Reinforcement Learning in Robotics(43), Sparse and Compressive Sensing Techniques(17), Machine Learning and Data Classification(13)

Publications150 total

A Unifying View of Coverage in Linear Off-Policy Evaluation
arXiv (Cornell University)·2026Open Access
A Unifying View of Coverage in Linear Off-Policy Evaluation
ArXiv.org·2026Open Access
The Coverage Principle: How Pre-Training Enables Post-Training
arXiv (Cornell University)·2025Open Access
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
arXiv (Cornell University)·2025Open Access
The Role of Environment Access in Agnostic Reinforcement Learning
arXiv (Cornell University)·2025Open Access
Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
arXiv (Cornell University)·2025Open Access
Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification
arXiv (Cornell University)·2025Open Access
Self-Improvement in Language Models: The Sharpening Mechanism
arXiv (Cornell University)·2024· 1 citedOpen Access
Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity
arXiv (Cornell University)·2024Open Access
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
arXiv (Cornell University)·2024Open Access
Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics
arXiv (Cornell University)·2024Open Access
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
arXiv (Cornell University)·2024· 1 citedOpen Access
Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
arXiv (Cornell University)·2024Open Access
Can large language models explore in-context?
arXiv (Cornell University)·2024· 2 citedOpen Access
Scalable Online Exploration via Coverability
arXiv (Cornell University)·2024· 1 citedOpen Access
Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning
arXiv (Cornell University)·2024Open Access
Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
2024· 1 cited
Can large language models explore in-context?
2024
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
arXiv (Cornell University)·2023Open Access
Robust Dynamic Assortment Optimization in the Presence of Outlier Customers
Operations Research·2023· 11 cited
page 1 of 8Next →

Frequent Co-authors

John Langford(17), Alekh Agarwal(16), Robert E. Schapire(7), Nan Jiang(6), Kirthevasan Kandasamy(6), Aarti Singh(6), Barnabás Póczos(5), Sham M. Kakade(5), Jordan T. Ash(4), Miroslav Dudı́k(4), Chicheng Zhang(3), Jeff Schneider(3), Hal Daumé(3), Vasilis Syrgkanis(3), Dipendra Misra(3), W. Sun(3), Haipeng Luo(3), Rajarshi Das(2), Shehzaad Dhuliawala(2), Manzil Zaheer(2)