AK
Akshay Krishnamurthy
cs.LGstat.MLcs.AIcs.CLmath.STstat.THmath.OCcs.ITmath.ITcs.DS
On Valency
published · living versionsW_hktak6f3·v1 · currentpublished
Off-policy evaluation for slate recommendation
with Adith Swaminathan, Alekh Agarwal, Miroslav Dudík, John Langford +2
1 version
Preprints & journals
101 papers in the corpus · 2012–2026Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents2610.07447v1 · Ziyang Cai, Christos Ziakas, Vasilis Kontonis et al.2026 · 0 citationsarXiv
Scaling Discovery through Test-Time Communication2609.21032v1 · Jongho Park, Vasilis Kontonis, Shivam Garg et al.2026 · 0 citationsarXiv
TailSFT: Filtered Fine-Tuning Improves Post-Training Performance2608.25756v1 · Sadhika Malladi, Samy Jelassi, Dylan Foster et al.2026 · 0 citationsarXiv
Learning to Reason with Curriculum II: Compositional Generalization2606.27721v1 · Nived Rajaraman, Audrey Huang, Miroslav Dudik et al.2026 · 0 citationsarXiv
Select and Improve: Understanding the Mechanics of Post-Training for Reasoning2606.13125v1 · Akshay Krishnamurthy, Audrey Huang, Nived Rajaraman2026 · 0 citationsarXiv
Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum2603.18325v2 · Nived Rajaraman, Audrey Huang, Miro Dudik et al.2026 · 0 citationsarXiv
Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference2603.07887v1 · Noah Golowich, Fan Chen, Dhruv Rohatgi et al.2026 · 0 citationsarXiv
A Unifying View of Coverage in Linear Off-Policy Evaluation2601.19030v1 · Philip Amortila, Audrey Huang, Akshay Krishnamurthy et al.2026 · 0 citationsarXiv
Wait, Wait, Wait... Why Do Reasoning Models Loop?2512.12895v3 · Charilaos Pipis, Shivam Garg, Vasilis Kontonis et al.2025 · 1 citationarXiv
The Coverage Principle: How Pre-Training Enables Post-Training2510.15020v2 · Fan Chen, Audrey Huang, Noah Golowich et al.2025 · 0 citationsarXiv
Representation-Based Exploration for Language Models: From Test-Time to Post-Training2510.11686v2 · Jens Tuyls, Dylan J. Foster, Akshay Krishnamurthy et al.2025 · 0 citationsarXiv
The Role of Environment Access in Agnostic Reinforcement Learning2504.05405v1 · Akshay Krishnamurthy, Gene Li, Ayush Sekhari2025 · 0 citationsarXiv
Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment2503.21878v2 · Audrey Huang, Adam Block, Qinghua Liu et al.2025 · 1 citationarXiv
Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification2502.12465v1 · Dhruv Rohatgi, Adam Block, Audrey Huang et al.2025 · 0 citationsarXiv
Self-Improvement in Language Models: The Sharpening Mechanism2412.01951v2 · Audrey Huang, Adam Block, Dylan J. Foster et al.2024 · 2 citationsarXiv
Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity2410.17904v1 · Philip Amortila, Dylan J. Foster, Nan Jiang et al.2024 · 1 citationarXiv
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization2407.13399v3 · Audrey Huang, Wenhao Zhan, Tengyang Xie et al.2024 · 0 citationsarXiv
Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics2406.11810v2 · Runzhe Wu, Ayush Sekhari, Akshay Krishnamurthy et al.2024 · 0 citationsarXiv
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF2405.21046v1 · Tengyang Xie, Dylan J. Foster, Akshay Krishnamurthy et al.2024 · 2 citationsarXiv
Rich-Observation Reinforcement Learning with Continuous Latent Dynamics2405.19269v1 · Yuda Song, Lili Wu, Dylan J. Foster et al.2024 · 0 citationsarXiv
Can large language models explore in-context?2403.15371v3 · Akshay Krishnamurthy, Keegan Harris, Dylan J. Foster et al.2024 · 10 citationsarXiv
Scalable Online Exploration via Coverability2403.06571v2 · Philip Amortila, Dylan J. Foster, Akshay Krishnamurthy2024 · 1 citationarXiv
Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning2401.12216v1 · Philip Amortila, Tongyi Cao, Akshay Krishnamurthy2024 · 0 citationsarXiv
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression2310.11428v1 · Adam Block, Dylan J. Foster, Akshay Krishnamurthy et al.2023 · 0 citationsarXiv
Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits2306.07923v2 · Lequn Wang, Akshay Krishnamurthy, Aleksandrs Slivkins2023 · 0 citationsarXiv
Exposing Attention Glitches with Flip-Flop Language Modeling2306.00946v2 · Bingbin Liu, Jordan T. Ash, Surbhi Goel et al.2023 · 12 citationsarXiv
Streaming Active Learning with Deep Neural Networks2303.02535v2 · Akanksha Saran, Safoora Yousefi, Akshay Krishnamurthy et al.2023 · 4 citationsarXiv
Learning Hidden Markov Models Using Conditional Samples2302.14753v2 · Sham M. Kakade, Akshay Krishnamurthy, Gaurav Mahajan et al.2023 · 0 citationsarXiv
Statistical Learning under Heterogeneous Distribution Shift2302.13934v4 · Max Simchowitz, Anurag Ajay, Pulkit Agrawal et al.2023 · 1 citationarXiv
Transformers Learn Shortcuts to Automata2210.10749v2 · Bingbin Liu, Jordan T. Ash, Surbhi Goel et al.2022 · 13 citationsarXiv
Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient2210.06718v3 · Yuda Song, Yifei Zhou, Ayush Sekhari et al.2022 · 10 citationsarXiv
Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models2207.08229v2 · Alex Lamb, Riashat Islam, Yonathan Efroni et al.2022 · 1 citationarXiv
On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL2206.10770v2 · Jinglin Chen, Aditya Modi, Akshay Krishnamurthy et al.2022 · 3 citationsarXiv
Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information2206.04282v1 · Yonathan Efroni, Dylan J. Foster, Dipendra Misra et al.2022 · 2 citationsarXiv
A Complete Characterization of Linear Estimators for Offline Policy Evaluation2203.04236v2 · Juan C. Perdomo, Akshay Krishnamurthy, Peter Bartlett et al.2022 · 0 citationsarXiv
Understanding Contrastive Learning Requires Incorporating Inductive Biases2202.14037v1 · Nikunj Saunshi, Jordan Ash, Surbhi Goel et al.2022 · 24 citationsarXiv
Provable Reinforcement Learning with a Short-Term Memory2202.03983v1 · Yonathan Efroni, Chi Jin, Akshay Krishnamurthy et al.2022 · 3 citationsarXiv
Efficient and Optimal Algorithms for Contextual Dueling Bandits under Realizability2111.12306v1 · Aadirupa Saha, Akshay Krishnamurthy2021 · 1 citationarXiv
Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation2111.10919v2 · Dylan J. Foster, Akshay Krishnamurthy, David Simchi-Levi et al.2021 · 5 citationsarXiv
Universal and data-adaptive algorithms for model selection in linear contextual bandits2111.04688v2 · Vidya Muthukumar, Akshay Krishnamurthy2021 · 1 citationarXiv
Anti-Concentrated Confidence Bonuses for Scalable Exploration2110.11202v2 · Jordan T. Ash, Cyril Zhang, Surbhi Goel et al.2021 · 1 citationInternational Conference on Learning Representations 2022
Provable RL with Exogenous Distractors via Multistep Inverse Dynamics2110.08847v2 · Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy et al.2021 · 3 citationsarXiv
Sparsity in Partially Controllable Linear Systems2110.06150v2 · Yonathan Efroni, Sham Kakade, Akshay Krishnamurthy et al.2021 · 0 citationsarXiv
Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination2107.02237v1 · Dylan J. Foster, Akshay Krishnamurthy2021 · 9 citationsarXiv
Bayesian decision-making under misspecified priors with applications to meta-learning2107.01509v1 · Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy et al.2021 · 9 citationsarXiv
Investigating the Role of Negatives in Contrastive Representation Learning2106.09943v1 · Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy et al.2021 · 11 citationsarXiv
Gone Fishing: Neural Active Learning with Fisher Embeddings2106.09675v2 · Jordan T. Ash, Surbhi Goel, Akshay Krishnamurthy et al.2021 · 25 citationsarXiv
Model-free Representation Learning and Exploration in Low-rank MDPs2102.07035v2 · Aditya Modi, Jinglin Chen, Akshay Krishnamurthy et al.2021 · 11 citationsarXiv
Learning the Linear Quadratic Regulator from Nonlinear Observations2010.03799v1 · Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz et al.2020 · 4 citationsarXiv
Private Reinforcement Learning with PAC and Regret Guarantees2009.09052v1 · Giuseppe Vietri, Borja Balle, Akshay Krishnamurthy et al.2020 · 23 citationsarXiv
Career total: 122 works. 101 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.