TailSFT: Filtered Fine-Tuning Improves Post-Training Performance
Sadhika Malladi, Samy Jelassi, Dylan Foster, Jordan Ash, Akshay Krishnamurthy
August 2026
arXiv | August 2026
Akshay Krishnamurthy
Senior Principal Researcher
论文与出版物
-
-
-
Learning to Reason with Curriculum II: Compositional Generalization
Nived Rajaraman, Audrey Huang, Miro Dudík, Robert E. Schapire, Dylan Foster, Akshay Krishnamurthy
June 2026
arXiv | June 2026
-
Select and Improve: Understanding the Mechanics of Post-Training for Reasoning
Akshay Krishnamurthy, Audrey Huang, Nived Rajaraman
June 2026
arXiv | June 2026
-
Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum
Nived Rajaraman, Audrey Huang, Miro Dudík, Robert E. Schapire, Dylan Foster, Akshay Krishnamurthy
COLT 2026 | March 2026
-
Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
Noah Golowich, Fan Chen, Dhruv Rohatgi, Raghav Singhal, Carles Domingo-Enrich, Dylan Foster, Akshay Krishnamurthy
March 2026
arXiv | March 2026
-
A Unifying View of Coverage in Linear Off-Policy Evaluation
P. Amortila, Audrey Huang, Akshay Krishnamurthy, Nan Jiang
ICLR 2026 | January 2026
-
-
-
Wait, Wait, Wait… Why Do Reasoning Models Loop?
Charilaos Pipis, Shivam Garg, Vasilis Kontonis, Vaishnavi Shrivastava, Akshay Krishnamurthy, Dimitris Papailiopoulos
ICML 2026 | December 2025
-
Next-Latent Prediction Transformers Learn Compact World Models
Jayden Teoh, Manan Tomar, Kwangjun Ahn, Edward J. Hu, Tim Pearce, Pratyusha Sharma, Akshay Krishnamurthy, Riashat Islam, Alex Lamb, John Langford
November 2025
arXiv | November 2025
-
The Coverage Principle: How Pre-Training Enables Post-Training
Fan Chen, Audrey Huang, Noah Golowich, Sadhika Malladi, Adam Block, Jordan Ash, Akshay Krishnamurthy, Dylan Foster
ICLR 2026 | October 2025
-
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Jens Tuyls, Dylan Foster, Akshay Krishnamurthy, Jordan Ash
ICLR 2026 | October 2025
-
Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
Audrey Huang, Adam Block, Qinghua Liu, Nan Jiang, Akshay Krishnamurthy, Dylan Foster
ICML 2025 | May 2025
-
The Role of Environment Access in Agnostic Reinforcement Learning
Akshay Krishnamurthy, Gene Li, Ayush Sekhari
COLT 2025 | April 2025
-
Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification
Dhruv Rohatgi, Adam Block, Audrey Huang, Akshay Krishnamurthy, Dylan Foster
COLT 2025 | February 2025
-
-
-
Self-Improvement in Language Models: The Sharpening Mechanism
Audrey Huang, Adam Block, Dylan Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan Ash, Akshay Krishnamurthy
ICLR 2025 | December 2024
-
Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
Philip Amortila, Dylan Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi
NeurIPS 2024 | October 2024
-
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
Audrey Huang, Wenhao Zhan, Tengyang Xie, Jason D. Lee, Wen Sun, Akshay Krishnamurthy, Dylan Foster
ICLR 2025 | July 2024
-
Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics
Runzhe Wu, Ayush Sekhari, Akshay Krishnamurthy, Wen Sun
ICLR 2025 | June 2024
-
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
Tengyang Xie, Dylan Foster, Akshay Krishnamurthy, Corby Rosset, Ahmed Awadallah, A. Rakhlin
ICLR 2025 | May 2024
-
Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy
ICML 2024 | May 2024
-
Can large language models explore in-context?
Akshay Krishnamurthy, Keegan Harris, Dylan Foster, Cyril Zhang, Aleksandrs Slivkins
NeurIPS 2024 | March 2024
-
Scalable Online Exploration via Coverability
P. Amortila, Dylan Foster, Akshay Krishnamurthy
ICML 2024 | March 2024
-
-
-
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
Adam Block, Dylan Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang
ICLR 2024 | October 2023
-
Exposing Attention Glitches with Flip-Flop Language Modeling
Bingbin Liu, Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang
NeurIPS 2023 | October 2023
-
Transformers Learn Shortcuts to Automata
Bingbin Liu, Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang
ICLR | May 2023
oral presentation
-
Streaming Active Learning with Deep Neural Networks
Akanksha Saran, Safoora Yousefi, Akshay Krishnamurthy, John Langford, Jordan Ash
ICML 2023 | March 2023
-
Statistical Learning under Heterogenous Distribution Shift
Max Simchowitz, Anurag Ajay, Pulkit Agrawal, Akshay Krishnamurthy
ICML 2023 | February 2023
-
-
-
Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation
Dylan Foster, Akshay Krishnamurthy, David Simchi-Levi, Yunzong Xu
Conference on Learning Theory | May 2022
-
Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information
Yonathan Efroni, Dylan Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford
Conference on Learning Theory | May 2022
-
Anti-Concentrated Confidence Bonuses for Scalable Exploration
Jordan T. Ash, Cyril Zhang, Surbhi Goel, Akshay Krishnamurthy, Sham M. Kakade
ICLR 2022 | April 2022
-
Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics
Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford
ICLR 2022 | April 2022
-
Investigating the Role of Negatives in Contrastive Representation Learning
Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Dipendra Misra
International Conference on Artificial Intelligence and Statistics | February 2022
-
-
-
Bayesian decision-making under misspecified priors with applications to meta-learning
Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu, Thodoris Lykouris, Miro Dudík, Robert E. Schapire
NeurIPS 2021 | December 2021
-
Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination
Dylan Foster, Akshay Krishnamurthy
NeurIPS 2021 | December 2021
-
Gone Fishing: Neural Active Learning with Fisher Embeddings
Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Sham Kakade
NeurIPS 2021 | December 2021
-
Provable RL with Exogenous Distractors via Multistep Inverse Dynamics
Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford
ICLR 2022 | October 2021
-
-
-
Learning the Linear Quadratic Regulator from Nonlinear Observations
Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz, Dipendra Misra, Wen Sun, Akshay Krishnamurthy, Alexander Rakhlin, John Langford
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS) 2020 | December 2020
-
Sample-Efficient Reinforcement Learning of Undercomplete POMDPs
Chi Jin, Sham Kakade, Akshay Krishnamurthy, Qinghua Liu
NeurIPS 2020 | November 2020
-
FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs
Alekh Agarwal, Sham Kakade, Akshay Krishnamurthy, Wen Sun
NeurIPS 2020 | October 2020
-
Information Theoretic Regret Bounds for Online Nonlinear Control
Sham Kakade, Akshay Krishnamurthy, Kendall Lowrey, Motoya Ohnishi, Wen Sun
NeurIPS 2020 | October 2020
-
Provably adaptive reinforcement learning in metric spaces
Tongyi Cao, Akshay Krishnamurthy
NeurIPS 2020 | October 2020
-
Contrastive learning, multi-view redundancy, and linear models
Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
August 2020
ArXiv preprint | August 2020
-
Doubly robust off-policy evaluation with shrinkage
Yi Su, Maria Dimakopoulou, Akshay Krishnamurthy, Miro Dudík
ICML 2020 | July 2020
-
Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning
Dipendra Misra, Mikael Henaff, Akshay Krishnamurthy, John Langford
ICML 2020 | July 2020
-
Private Reinforcement Learning with PAC and Regret Guarantees
Giuseppe Vietri, Borja Balle, Akshay Krishnamurthy, Steven Wu
ICML 2020 | July 2020
-
Reward-Free Exploration for Reinforcement Learning
Chi Jin, Akshay Krishnamurthy, Max Simchowitz, Tiancheng Yu
ICML 2020 | July 2020
-
Efficient Contextual Bandits With Continuous Actions
Maryam Majzoubi, Chicheng Zhang, Rajan Chari, Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins
NeurIPS 2020 | June 2020
-
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, Alekh Agarwal
Eighth International Conference on Learning Representations (ICLR) | April 2020
-
Contrastive Estimation Reveals Topic Posterior Information To Linear Models
Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
March 2020
ArXiv | March 2020
-
Adaptive Estimator Selection for Off-Policy Evaluation
Yi-Hsun Su, Pavithra Srinath, Akshay Krishnamurthy
ICML | February 2020
-
Corrupted Multidimensional Binary Search: Learning In The Presence Of Irrational Agents
Akshay Krishnamurthy, Thodoris Lykouris, Chara Podimata
arXiv preprint arXiv:2002.11650 | February 2020
-
-
-
Model selection for contextual bandits
Dylan Foster, Akshay Krishnamurthy, Haipeng Luo
Advances in Neural Information Processing Systems | December 2019
-
Trace Reconstruction: Generalized and Parametrized
Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor, Soumyabrata Pal
European Symposium on Algorithms | September 2019
-
Scalable Hierarchical Clustering via Tree Grafting
Nicholas Monath, Ari Kobren, Akshay Krishnamurthy, Michael Glass, Andrew McCallum
Knowledge Discovery and Data Mining | August 2019
-
Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting
Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins, Chicheng Zhang
Conference on Learning Theory | June 2019
-
Disagreement-based combinatorial pure exploration: Sample complexity bounds and an efficient algorithm
Tongyi Cao, Akshay Krishnamurthy
Conference on Learning Theory | June 2019
-
Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches
Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford
Conference on Learning Theory | June 2019
-
Myopic posterior sampling for adaptive goal oriented design of experiments
Kirthevasan Kandasamy, Willie Neiswanger, Reed Zhang, Akshay Krishnamurthy, Jeff Schneider, Barnabas Poczos
International Conference on Machine Learning | June 2019
-
Provably efficient RL with Rich Observations via Latent State Decoding
Simon Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miro Dudík, John Langford
International Conference on Machine Learning | June 2019
-
Active Learning for Cost-Sensitive Classification
Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang, John Langford, Hal Daumé III
Journal of Machine Learning Research | April 2019
-
-
-
Contextual bandits with surrogate losses: Margin bounds and efficient algorithms
Dylan J. Foster, Akshay Krishnamurthy
Advances in Neural Information Processing Systems | December 2018
-
Extreme compressive sampling for covariance estimation
Martin Azizyan, Akshay Krishnamurthy, Aarti Singh
IEEE Transactions on Information Theory | December 2018
-
On Oracle-Efficient PAC Reinforcement Learning with Rich Observations
Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
Advances in Neural Information Processing Systems | December 2018
-
Model-Based Reinforcement Learning in Contextual Decision Processes
Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford
November 2018
November 2018
-
Semiparametric Contextual Bandits
Akshay Krishnamurthy, Zhiwei Steven Wu, Vasilis Syrgkanis
International Conference on Machine Learning | July 2018
arXiv
-
Asynchronous Parallel Bayesian Optimisation via Thompson Sampling
Kirthevasan Kandasamy, Akshay Krishnamurthy, Jeff Schneider, Barnabas Poczos
Artificial Intelligence and Statistics | April 2018
-
Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alex Smola, Andrew McCallum
International Conference on Learning Representations | April 2018
-
-
-
Off-Policy Evaluation For Slate Recommendation
Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miro Dudík, John Langford, Damien Jose, Imed Zitouni
Neural Information Processing Systems | December 2017
-
Contextual Decision Processes with low Bellman rank are PAC-Learnable
Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
International Conference on Machine Learning | August 2017
-
An online hierarchical algorithm for extreme clustering
Ari Kobren, Akshay Krishnamurthy, Nicholas Monath, Andrew McCallum
Knowledge Discovery and Data Mining | August 2017
-
Open Problem: First-Order Regret Bounds for Contextual Bandits
Alekh Agarwal, Akshay Krishnamurthy, John Langford, Haipeng Luo, Robert E. Schapire
Conference on Learning Theory | July 2017
-
-
-
Contextual Semibandits via Supervised Learning Oracles
Akshay Krishnamurthy, Alekh Agarwal, Miro Dudík
Advances in Neural Information Processing Systems | December 2016
-
Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits
Vasilis Syrgkanis, Haipeng Luo, Akshay Krishnamurthy, Robert E. Schapire
Advances in Neural Information Processing Systems | December 2016
-
PAC Reinforcement Learning with Rich Observations
Akshay Krishnamurthy, Alekh Agarwal, John Langford
Advances in Neural Information Processing Systems | December 2016
-
Minimax Structured Normal Means Inference
IEEE International Symposium on Information Theory | July 2016
-
Efficient Algorithms for Adversarial Contextual Learning
Vasilis Syrgkanis, Akshay Krishnamurthy, Robert E. Schapire
International Conference on Machine Learning | June 2016
-
-
-
Nonparametric von Mises estimators for entropies, divergences, and mutual informations
Kirthevasan Kandasamy, Akshay Krishnamurthy, Barnabas Poczos, Larry Wasserman, James M. Robins
Advances in Neural Information Processing Systems | December 2015
-
Learning to Search Better than Your Teacher
Kai-Wei Chang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Hal Daumé III
International Conference on Machine Learning | July 2015
-
On Estimating L_2^2 Divergence
Akshay Krishnamurthy, Kirthevasan Kandasamy, Barnabas Poczos, Larry Wasserman
Artificial Intelligence and Statistics | May 2015
-
-
-
Subspace learning from extremely compressed measurements
Akshay Krishnamurthy, Martin Azizyan, Aarti Singh
Asilomar Conference on Signals, Systems, and Computers | November 2014
-
Nonparametric Estimation of Renyi Divergence and Friends
Akshay Krishnamurthy, Kirthevasan Kandasamy, Barnabas Poczos, Larry Wasserman
International Conference on Machine Learning | July 2014
-
-
-
Low-Rank Matrix and Tensor Completion via Adaptive Sampling
Akshay Krishnamurthy, Aarti Singh
Advances in Neural Information Processing Systems | December 2013
-
Near-optimal anomaly detection in graphs using Lovasz extended scan statistic
James Sharpnack, Akshay Krishnamurthy, Aarti Singh
Advances in Neural Information Processing Systems | December 2013
-
Recovering graph-structured activations using adaptive compressive measurements
Akshay Krishnamurthy (akshaykr), James Sharpnack, Aarti Singh
Asilomar Conference on Signals, Systems, and Computers | November 2013
-
Detecting activations over graphs using spanning tree wavelet bases
James Sharpnack, Akshay Krishnamurthy, Aarti Singh
Artificial Intelligence and Statistics | April 2013
-
-
-
Completion of high-rank ultrametric matrices using selective entries
Aarti Singh, Akshay Krishnamurthy, Sivaraman Balakrishnan, Min Xu
International Conference on Signal Processing and Communication | July 2012
-
Efficient active algorithms for hierarchical clustering
Akshay Krishnamurthy, Sivaraman Balakrishnan, Min Xu, Aarti Singh
International Conference on Machine Learning | June 2012
-
Robust multi-source network tomography using selective probes
Akshay Krishnamurthy, Aarti Singh
IEEE Infocom | March 2012
-
-
-
Noise Thresholds for Spectral Clustering
Sivaraman Balakrishnan, Min Xu, Akshay Krishnamurthy, Aarti Singh
Advances in Neural Information Processing Systems | December 2011
-
-
-
TailSFT: Filtered Fine-Tuning Improves Post-Training Performance
Sadhika Malladi, Samy Jelassi, Dylan Foster, Jordan Ash, Akshay Krishnamurthy
August 2026
arXiv | August 2026
-
Learning to Reason with Curriculum II: Compositional Generalization
Nived Rajaraman, Audrey Huang, Miro Dudík, Robert E. Schapire, Dylan Foster, Akshay Krishnamurthy
June 2026
arXiv | June 2026
-
Select and Improve: Understanding the Mechanics of Post-Training for Reasoning
Akshay Krishnamurthy, Audrey Huang, Nived Rajaraman
June 2026
arXiv | June 2026
-
Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum
Nived Rajaraman, Audrey Huang, Miro Dudík, Robert E. Schapire, Dylan Foster, Akshay Krishnamurthy
COLT 2026 | March 2026
-
Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
Noah Golowich, Fan Chen, Dhruv Rohatgi, Raghav Singhal, Carles Domingo-Enrich, Dylan Foster, Akshay Krishnamurthy
March 2026
arXiv | March 2026
-
A Unifying View of Coverage in Linear Off-Policy Evaluation
P. Amortila, Audrey Huang, Akshay Krishnamurthy, Nan Jiang
ICLR 2026 | January 2026
-
Wait, Wait, Wait… Why Do Reasoning Models Loop?
Charilaos Pipis, Shivam Garg, Vasilis Kontonis, Vaishnavi Shrivastava, Akshay Krishnamurthy, Dimitris Papailiopoulos
ICML 2026 | December 2025
-
Next-Latent Prediction Transformers Learn Compact World Models
Jayden Teoh, Manan Tomar, Kwangjun Ahn, Edward J. Hu, Tim Pearce, Pratyusha Sharma, Akshay Krishnamurthy, Riashat Islam, Alex Lamb, John Langford
November 2025
arXiv | November 2025
-
The Coverage Principle: How Pre-Training Enables Post-Training
Fan Chen, Audrey Huang, Noah Golowich, Sadhika Malladi, Adam Block, Jordan Ash, Akshay Krishnamurthy, Dylan Foster
ICLR 2026 | October 2025
-
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Jens Tuyls, Dylan Foster, Akshay Krishnamurthy, Jordan Ash
ICLR 2026 | October 2025
-
Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
Audrey Huang, Adam Block, Qinghua Liu, Nan Jiang, Akshay Krishnamurthy, Dylan Foster
ICML 2025 | May 2025
-
The Role of Environment Access in Agnostic Reinforcement Learning
Akshay Krishnamurthy, Gene Li, Ayush Sekhari
COLT 2025 | April 2025
-
Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification
Dhruv Rohatgi, Adam Block, Audrey Huang, Akshay Krishnamurthy, Dylan Foster
COLT 2025 | February 2025
-
Self-Improvement in Language Models: The Sharpening Mechanism
Audrey Huang, Adam Block, Dylan Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan Ash, Akshay Krishnamurthy
ICLR 2025 | December 2024
-
Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
Philip Amortila, Dylan Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi
NeurIPS 2024 | October 2024
-
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
Audrey Huang, Wenhao Zhan, Tengyang Xie, Jason D. Lee, Wen Sun, Akshay Krishnamurthy, Dylan Foster
ICLR 2025 | July 2024
-
Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics
Runzhe Wu, Ayush Sekhari, Akshay Krishnamurthy, Wen Sun
ICLR 2025 | June 2024
-
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
Tengyang Xie, Dylan Foster, Akshay Krishnamurthy, Corby Rosset, Ahmed Awadallah, A. Rakhlin
ICLR 2025 | May 2024
-
Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy
ICML 2024 | May 2024
-
Can large language models explore in-context?
Akshay Krishnamurthy, Keegan Harris, Dylan Foster, Cyril Zhang, Aleksandrs Slivkins
NeurIPS 2024 | March 2024
-
Scalable Online Exploration via Coverability
P. Amortila, Dylan Foster, Akshay Krishnamurthy
ICML 2024 | March 2024
-
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
Adam Block, Dylan Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang
ICLR 2024 | October 2023
-
Exposing Attention Glitches with Flip-Flop Language Modeling
Bingbin Liu, Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang
NeurIPS 2023 | October 2023
-
Transformers Learn Shortcuts to Automata
Bingbin Liu, Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang
ICLR | May 2023
oral presentation
-
Streaming Active Learning with Deep Neural Networks
Akanksha Saran, Safoora Yousefi, Akshay Krishnamurthy, John Langford, Jordan Ash
ICML 2023 | March 2023
-
Statistical Learning under Heterogenous Distribution Shift
Max Simchowitz, Anurag Ajay, Pulkit Agrawal, Akshay Krishnamurthy
ICML 2023 | February 2023
-
Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information
Yonathan Efroni, Dylan Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford
Conference on Learning Theory | May 2022
-
Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation
Dylan Foster, Akshay Krishnamurthy, David Simchi-Levi, Yunzong Xu
Conference on Learning Theory | May 2022
-
Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics
Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford
ICLR 2022 | April 2022
-
Anti-Concentrated Confidence Bonuses for Scalable Exploration
Jordan T. Ash, Cyril Zhang, Surbhi Goel, Akshay Krishnamurthy, Sham M. Kakade
ICLR 2022 | April 2022
-
Investigating the Role of Negatives in Contrastive Representation Learning
Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Dipendra Misra
International Conference on Artificial Intelligence and Statistics | February 2022
-
Bayesian decision-making under misspecified priors with applications to meta-learning
Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu, Thodoris Lykouris, Miro Dudík, Robert E. Schapire
NeurIPS 2021 | December 2021
-
Gone Fishing: Neural Active Learning with Fisher Embeddings
Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Sham Kakade
NeurIPS 2021 | December 2021
-
Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination
Dylan Foster, Akshay Krishnamurthy
NeurIPS 2021 | December 2021
-
Provable RL with Exogenous Distractors via Multistep Inverse Dynamics
Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford
ICLR 2022 | October 2021
-
Learning the Linear Quadratic Regulator from Nonlinear Observations
Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz, Dipendra Misra, Wen Sun, Akshay Krishnamurthy, Alexander Rakhlin, John Langford
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS) 2020 | December 2020
-
Sample-Efficient Reinforcement Learning of Undercomplete POMDPs
Chi Jin, Sham Kakade, Akshay Krishnamurthy, Qinghua Liu
NeurIPS 2020 | November 2020
-
Provably adaptive reinforcement learning in metric spaces
Tongyi Cao, Akshay Krishnamurthy
NeurIPS 2020 | October 2020
-
Information Theoretic Regret Bounds for Online Nonlinear Control
Sham Kakade, Akshay Krishnamurthy, Kendall Lowrey, Motoya Ohnishi, Wen Sun
NeurIPS 2020 | October 2020
-
FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs
Alekh Agarwal, Sham Kakade, Akshay Krishnamurthy, Wen Sun
NeurIPS 2020 | October 2020
-
Contrastive learning, multi-view redundancy, and linear models
Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
August 2020
ArXiv preprint | August 2020
-
Private Reinforcement Learning with PAC and Regret Guarantees
Giuseppe Vietri, Borja Balle, Akshay Krishnamurthy, Steven Wu
ICML 2020 | July 2020
-
Reward-Free Exploration for Reinforcement Learning
Chi Jin, Akshay Krishnamurthy, Max Simchowitz, Tiancheng Yu
ICML 2020 | July 2020
-
Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning
Dipendra Misra, Mikael Henaff, Akshay Krishnamurthy, John Langford
ICML 2020 | July 2020
-
Doubly robust off-policy evaluation with shrinkage
Yi Su, Maria Dimakopoulou, Akshay Krishnamurthy, Miro Dudík
ICML 2020 | July 2020
-
Efficient Contextual Bandits With Continuous Actions
Maryam Majzoubi, Chicheng Zhang, Rajan Chari, Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins
NeurIPS 2020 | June 2020
-
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, Alekh Agarwal
Eighth International Conference on Learning Representations (ICLR) | April 2020
-
Contrastive Estimation Reveals Topic Posterior Information To Linear Models
Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
March 2020
ArXiv | March 2020
-
Adaptive Estimator Selection for Off-Policy Evaluation
Yi-Hsun Su, Pavithra Srinath, Akshay Krishnamurthy
ICML | February 2020
-
Model selection for contextual bandits
Dylan Foster, Akshay Krishnamurthy, Haipeng Luo
Advances in Neural Information Processing Systems | December 2019
-
Scalable Hierarchical Clustering via Tree Grafting
Nicholas Monath, Ari Kobren, Akshay Krishnamurthy, Michael Glass, Andrew McCallum
Knowledge Discovery and Data Mining | August 2019
-
Disagreement-based combinatorial pure exploration: Sample complexity bounds and an efficient algorithm
Tongyi Cao, Akshay Krishnamurthy
Conference on Learning Theory | June 2019
-
Myopic posterior sampling for adaptive goal oriented design of experiments
Kirthevasan Kandasamy, Willie Neiswanger, Reed Zhang, Akshay Krishnamurthy, Jeff Schneider, Barnabas Poczos
International Conference on Machine Learning | June 2019
-
Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting
Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins, Chicheng Zhang
Conference on Learning Theory | June 2019
-
Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches
Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford
Conference on Learning Theory | June 2019
-
Provably efficient RL with Rich Observations via Latent State Decoding
Simon Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miro Dudík, John Langford
International Conference on Machine Learning | June 2019
-
Active Learning for Cost-Sensitive Classification
Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang, John Langford, Hal Daumé III
Journal of Machine Learning Research | April 2019
-
Extreme compressive sampling for covariance estimation
Martin Azizyan, Akshay Krishnamurthy, Aarti Singh
IEEE Transactions on Information Theory | December 2018
-
On Oracle-Efficient PAC Reinforcement Learning with Rich Observations
Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
Advances in Neural Information Processing Systems | December 2018
-
Contextual bandits with surrogate losses: Margin bounds and efficient algorithms
Dylan J. Foster, Akshay Krishnamurthy
Advances in Neural Information Processing Systems | December 2018
-
Model-Based Reinforcement Learning in Contextual Decision Processes
Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford
November 2018
November 2018
-
Semiparametric Contextual Bandits
Akshay Krishnamurthy, Zhiwei Steven Wu, Vasilis Syrgkanis
International Conference on Machine Learning | July 2018
arXiv
-
Asynchronous Parallel Bayesian Optimisation via Thompson Sampling
Kirthevasan Kandasamy, Akshay Krishnamurthy, Jeff Schneider, Barnabas Poczos
Artificial Intelligence and Statistics | April 2018
-
Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alex Smola, Andrew McCallum
International Conference on Learning Representations | April 2018
-
Off-Policy Evaluation For Slate Recommendation
Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miro Dudík, John Langford, Damien Jose, Imed Zitouni
Neural Information Processing Systems | December 2017
-
Contextual Decision Processes with low Bellman rank are PAC-Learnable
Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
International Conference on Machine Learning | August 2017
-
An online hierarchical algorithm for extreme clustering
Ari Kobren, Akshay Krishnamurthy, Nicholas Monath, Andrew McCallum
Knowledge Discovery and Data Mining | August 2017
-
Open Problem: First-Order Regret Bounds for Contextual Bandits
Alekh Agarwal, Akshay Krishnamurthy, John Langford, Haipeng Luo, Robert E. Schapire
Conference on Learning Theory | July 2017
-
PAC Reinforcement Learning with Rich Observations
Akshay Krishnamurthy, Alekh Agarwal, John Langford
Advances in Neural Information Processing Systems | December 2016
-
Contextual Semibandits via Supervised Learning Oracles
Akshay Krishnamurthy, Alekh Agarwal, Miro Dudík
Advances in Neural Information Processing Systems | December 2016
-
Minimax Structured Normal Means Inference
IEEE International Symposium on Information Theory | July 2016
-
Efficient Algorithms for Adversarial Contextual Learning
Vasilis Syrgkanis, Akshay Krishnamurthy, Robert E. Schapire
International Conference on Machine Learning | June 2016
-
Nonparametric von Mises estimators for entropies, divergences, and mutual informations
Kirthevasan Kandasamy, Akshay Krishnamurthy, Barnabas Poczos, Larry Wasserman, James M. Robins
Advances in Neural Information Processing Systems | December 2015
-
Learning to Search Better than Your Teacher
Kai-Wei Chang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Hal Daumé III
International Conference on Machine Learning | July 2015
-
On Estimating L_2^2 Divergence
Akshay Krishnamurthy, Kirthevasan Kandasamy, Barnabas Poczos, Larry Wasserman
Artificial Intelligence and Statistics | May 2015
-
Subspace learning from extremely compressed measurements
Akshay Krishnamurthy, Martin Azizyan, Aarti Singh
Asilomar Conference on Signals, Systems, and Computers | November 2014
-
Nonparametric Estimation of Renyi Divergence and Friends
Akshay Krishnamurthy, Kirthevasan Kandasamy, Barnabas Poczos, Larry Wasserman
International Conference on Machine Learning | July 2014
-
Near-optimal anomaly detection in graphs using Lovasz extended scan statistic
James Sharpnack, Akshay Krishnamurthy, Aarti Singh
Advances in Neural Information Processing Systems | December 2013
-
Low-Rank Matrix and Tensor Completion via Adaptive Sampling
Akshay Krishnamurthy, Aarti Singh
Advances in Neural Information Processing Systems | December 2013
-
Recovering graph-structured activations using adaptive compressive measurements
Akshay Krishnamurthy (akshaykr), James Sharpnack, Aarti Singh
Asilomar Conference on Signals, Systems, and Computers | November 2013
-
Detecting activations over graphs using spanning tree wavelet bases
James Sharpnack, Akshay Krishnamurthy, Aarti Singh
Artificial Intelligence and Statistics | April 2013
-
Completion of high-rank ultrametric matrices using selective entries
Aarti Singh, Akshay Krishnamurthy, Sivaraman Balakrishnan, Min Xu
International Conference on Signal Processing and Communication | July 2012
-
Efficient active algorithms for hierarchical clustering
Akshay Krishnamurthy, Sivaraman Balakrishnan, Min Xu, Aarti Singh
International Conference on Machine Learning | June 2012
-
Robust multi-source network tomography using selective probes
Akshay Krishnamurthy, Aarti Singh
IEEE Infocom | March 2012
-
Noise Thresholds for Spectral Clustering
Sivaraman Balakrishnan, Min Xu, Akshay Krishnamurthy, Aarti Singh
Advances in Neural Information Processing Systems | December 2011
-
-
-
Self-Improvement in Language Models: The Sharpening Mechanism
Audrey Huang, Adam Block, Dylan Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan Ash, Akshay Krishnamurthy
ICLR 2025 | December 2024
-
FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs
Alekh Agarwal, Sham Kakade, Akshay Krishnamurthy, Wen Sun
NeurIPS 2020 | October 2020
-
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, Alekh Agarwal
Eighth International Conference on Learning Representations (ICLR) | April 2020
-
Contrastive Estimation Reveals Topic Posterior Information To Linear Models
Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
March 2020
ArXiv | March 2020
-
Corrupted Multidimensional Binary Search: Learning In The Presence Of Irrational Agents
Akshay Krishnamurthy, Thodoris Lykouris, Chara Podimata
arXiv preprint arXiv:2002.11650 | February 2020
-
Trace Reconstruction: Generalized and Parametrized
Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor, Soumyabrata Pal
European Symposium on Algorithms | September 2019
-
Contextual bandits with surrogate losses: Margin bounds and efficient algorithms
Dylan J. Foster, Akshay Krishnamurthy
Advances in Neural Information Processing Systems | December 2018
-
Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits
Vasilis Syrgkanis, Haipeng Luo, Akshay Krishnamurthy, Robert E. Schapire
Advances in Neural Information Processing Systems | December 2016
-
Efficient Algorithms for Adversarial Contextual Learning
Vasilis Syrgkanis, Akshay Krishnamurthy, Robert E. Schapire
International Conference on Machine Learning | June 2016
-
-
-
Learning the Linear Quadratic Regulator from Nonlinear Observations
Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz, Dipendra Misra, Wen Sun, Akshay Krishnamurthy, Alexander Rakhlin, John Langford
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS) 2020 | December 2020
-
-
-
Semiparametric Contextual Bandits
Akshay Krishnamurthy, Zhiwei Steven Wu, Vasilis Syrgkanis
International Conference on Machine Learning | July 2018
arXiv
-
-
-
Off-Policy Evaluation For Slate Recommendation
Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miro Dudík, John Langford, Damien Jose, Imed Zitouni
Neural Information Processing Systems | December 2017
-
-
-
Learning to Reason with Curriculum I: Provable Benefits of Autocurriculum
Nived Rajaraman, Audrey Huang, Miro Dudík, Robert E. Schapire, Dylan Foster, Akshay Krishnamurthy
COLT 2026 | March 2026
-
A Unifying View of Coverage in Linear Off-Policy Evaluation
P. Amortila, Audrey Huang, Akshay Krishnamurthy, Nan Jiang
ICLR 2026 | January 2026
-
Wait, Wait, Wait… Why Do Reasoning Models Loop?
Charilaos Pipis, Shivam Garg, Vasilis Kontonis, Vaishnavi Shrivastava, Akshay Krishnamurthy, Dimitris Papailiopoulos
ICML 2026 | December 2025
-
The Coverage Principle: How Pre-Training Enables Post-Training
Fan Chen, Audrey Huang, Noah Golowich, Sadhika Malladi, Adam Block, Jordan Ash, Akshay Krishnamurthy, Dylan Foster
ICLR 2026 | October 2025
-
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Jens Tuyls, Dylan Foster, Akshay Krishnamurthy, Jordan Ash
ICLR 2026 | October 2025
-
Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment
Audrey Huang, Adam Block, Qinghua Liu, Nan Jiang, Akshay Krishnamurthy, Dylan Foster
ICML 2025 | May 2025
-
The Role of Environment Access in Agnostic Reinforcement Learning
Akshay Krishnamurthy, Gene Li, Ayush Sekhari
COLT 2025 | April 2025
-
Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification
Dhruv Rohatgi, Adam Block, Audrey Huang, Akshay Krishnamurthy, Dylan Foster
COLT 2025 | February 2025
-
Self-Improvement in Language Models: The Sharpening Mechanism
Audrey Huang, Adam Block, Dylan Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan Ash, Akshay Krishnamurthy
ICLR 2025 | December 2024
-
Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
Philip Amortila, Dylan Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi
NeurIPS 2024 | October 2024
-
Correcting the Mythos of KL-Regularization: Direct Alignment without Overoptimization via Chi-Squared Preference Optimization
Audrey Huang, Wenhao Zhan, Tengyang Xie, Jason D. Lee, Wen Sun, Akshay Krishnamurthy, Dylan Foster
ICLR 2025 | July 2024
-
Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics
Runzhe Wu, Ayush Sekhari, Akshay Krishnamurthy, Wen Sun
ICLR 2025 | June 2024
-
Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF
Tengyang Xie, Dylan Foster, Akshay Krishnamurthy, Corby Rosset, Ahmed Awadallah, A. Rakhlin
ICLR 2025 | May 2024
-
Rich-Observation Reinforcement Learning with Continuous Latent Dynamics
Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy
ICML 2024 | May 2024
-
Can large language models explore in-context?
Akshay Krishnamurthy, Keegan Harris, Dylan Foster, Cyril Zhang, Aleksandrs Slivkins
NeurIPS 2024 | March 2024
-
Scalable Online Exploration via Coverability
P. Amortila, Dylan Foster, Akshay Krishnamurthy
ICML 2024 | March 2024
-
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
Adam Block, Dylan Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang
ICLR 2024 | October 2023
-
Exposing Attention Glitches with Flip-Flop Language Modeling
Bingbin Liu, Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang
NeurIPS 2023 | October 2023
-
Transformers Learn Shortcuts to Automata
Bingbin Liu, Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Cyril Zhang
ICLR | May 2023
oral presentation
-
Streaming Active Learning with Deep Neural Networks
Akanksha Saran, Safoora Yousefi, Akshay Krishnamurthy, John Langford, Jordan Ash
ICML 2023 | March 2023
-
Statistical Learning under Heterogenous Distribution Shift
Max Simchowitz, Anurag Ajay, Pulkit Agrawal, Akshay Krishnamurthy
ICML 2023 | February 2023
-
Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information
Yonathan Efroni, Dylan Foster, Dipendra Misra, Akshay Krishnamurthy, John Langford
Conference on Learning Theory | May 2022
-
Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation
Dylan Foster, Akshay Krishnamurthy, David Simchi-Levi, Yunzong Xu
Conference on Learning Theory | May 2022
-
Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics
Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford
ICLR 2022 | April 2022
-
Anti-Concentrated Confidence Bonuses for Scalable Exploration
Jordan T. Ash, Cyril Zhang, Surbhi Goel, Akshay Krishnamurthy, Sham M. Kakade
ICLR 2022 | April 2022
-
Investigating the Role of Negatives in Contrastive Representation Learning
Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Dipendra Misra
International Conference on Artificial Intelligence and Statistics | February 2022
-
Bayesian decision-making under misspecified priors with applications to meta-learning
Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu, Thodoris Lykouris, Miro Dudík, Robert E. Schapire
NeurIPS 2021 | December 2021
-
Gone Fishing: Neural Active Learning with Fisher Embeddings
Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, Sham Kakade
NeurIPS 2021 | December 2021
-
Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination
Dylan Foster, Akshay Krishnamurthy
NeurIPS 2021 | December 2021
-
Provable RL with Exogenous Distractors via Multistep Inverse Dynamics
Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford
ICLR 2022 | October 2021
-
Learning the Linear Quadratic Regulator from Nonlinear Observations
Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz, Dipendra Misra, Wen Sun, Akshay Krishnamurthy, Alexander Rakhlin, John Langford
Thirty-fourth Conference on Neural Information Processing Systems (NeurIPS) 2020 | December 2020
-
Sample-Efficient Reinforcement Learning of Undercomplete POMDPs
Chi Jin, Sham Kakade, Akshay Krishnamurthy, Qinghua Liu
NeurIPS 2020 | November 2020
-
Provably adaptive reinforcement learning in metric spaces
Tongyi Cao, Akshay Krishnamurthy
NeurIPS 2020 | October 2020
-
Information Theoretic Regret Bounds for Online Nonlinear Control
Sham Kakade, Akshay Krishnamurthy, Kendall Lowrey, Motoya Ohnishi, Wen Sun
NeurIPS 2020 | October 2020
-
FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs
Alekh Agarwal, Sham Kakade, Akshay Krishnamurthy, Wen Sun
NeurIPS 2020 | October 2020
-
Private Reinforcement Learning with PAC and Regret Guarantees
Giuseppe Vietri, Borja Balle, Akshay Krishnamurthy, Steven Wu
ICML 2020 | July 2020
-
Reward-Free Exploration for Reinforcement Learning
Chi Jin, Akshay Krishnamurthy, Max Simchowitz, Tiancheng Yu
ICML 2020 | July 2020
-
Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning
Dipendra Misra, Mikael Henaff, Akshay Krishnamurthy, John Langford
ICML 2020 | July 2020
-
Doubly robust off-policy evaluation with shrinkage
Yi Su, Maria Dimakopoulou, Akshay Krishnamurthy, Miro Dudík
ICML 2020 | July 2020
-
Efficient Contextual Bandits With Continuous Actions
Maryam Majzoubi, Chicheng Zhang, Rajan Chari, Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins
NeurIPS 2020 | June 2020
-
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, Alekh Agarwal
Eighth International Conference on Learning Representations (ICLR) | April 2020
-
Adaptive Estimator Selection for Off-Policy Evaluation
Yi-Hsun Su, Pavithra Srinath, Akshay Krishnamurthy
ICML | February 2020
-
Model selection for contextual bandits
Dylan Foster, Akshay Krishnamurthy, Haipeng Luo
Advances in Neural Information Processing Systems | December 2019
-
Trace Reconstruction: Generalized and Parametrized
Akshay Krishnamurthy, Arya Mazumdar, Andrew McGregor, Soumyabrata Pal
European Symposium on Algorithms | September 2019
-
Scalable Hierarchical Clustering via Tree Grafting
Nicholas Monath, Ari Kobren, Akshay Krishnamurthy, Michael Glass, Andrew McCallum
Knowledge Discovery and Data Mining | August 2019
-
Disagreement-based combinatorial pure exploration: Sample complexity bounds and an efficient algorithm
Tongyi Cao, Akshay Krishnamurthy
Conference on Learning Theory | June 2019
-
Myopic posterior sampling for adaptive goal oriented design of experiments
Kirthevasan Kandasamy, Willie Neiswanger, Reed Zhang, Akshay Krishnamurthy, Jeff Schneider, Barnabas Poczos
International Conference on Machine Learning | June 2019
-
Contextual Bandits with Continuous Actions: Smoothing, Zooming, and Adapting
Akshay Krishnamurthy, John Langford, Aleksandrs Slivkins, Chicheng Zhang
Conference on Learning Theory | June 2019
-
Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches
Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford
Conference on Learning Theory | June 2019
-
Provably efficient RL with Rich Observations via Latent State Decoding
Simon Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miro Dudík, John Langford
International Conference on Machine Learning | June 2019
-
On Oracle-Efficient PAC Reinforcement Learning with Rich Observations
Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
Advances in Neural Information Processing Systems | December 2018
-
Contextual bandits with surrogate losses: Margin bounds and efficient algorithms
Dylan J. Foster, Akshay Krishnamurthy
Advances in Neural Information Processing Systems | December 2018
-
Semiparametric Contextual Bandits
Akshay Krishnamurthy, Zhiwei Steven Wu, Vasilis Syrgkanis
International Conference on Machine Learning | July 2018
arXiv
-
Asynchronous Parallel Bayesian Optimisation via Thompson Sampling
Kirthevasan Kandasamy, Akshay Krishnamurthy, Jeff Schneider, Barnabas Poczos
Artificial Intelligence and Statistics | April 2018
-
Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning
Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, Luke Vilnis, Ishan Durugkar, Akshay Krishnamurthy, Alex Smola, Andrew McCallum
International Conference on Learning Representations | April 2018
-
Off-Policy Evaluation For Slate Recommendation
Adith Swaminathan, Akshay Krishnamurthy, Alekh Agarwal, Miro Dudík, John Langford, Damien Jose, Imed Zitouni
Neural Information Processing Systems | December 2017
-
Contextual Decision Processes with low Bellman rank are PAC-Learnable
Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
International Conference on Machine Learning | August 2017
-
An online hierarchical algorithm for extreme clustering
Ari Kobren, Akshay Krishnamurthy, Nicholas Monath, Andrew McCallum
Knowledge Discovery and Data Mining | August 2017
-
Open Problem: First-Order Regret Bounds for Contextual Bandits
Alekh Agarwal, Akshay Krishnamurthy, John Langford, Haipeng Luo, Robert E. Schapire
Conference on Learning Theory | July 2017
-
Improved Regret Bounds for Oracle-Based Adversarial Contextual Bandits
Vasilis Syrgkanis, Haipeng Luo, Akshay Krishnamurthy, Robert E. Schapire
Advances in Neural Information Processing Systems | December 2016
-
PAC Reinforcement Learning with Rich Observations
Akshay Krishnamurthy, Alekh Agarwal, John Langford
Advances in Neural Information Processing Systems | December 2016
-
Contextual Semibandits via Supervised Learning Oracles
Akshay Krishnamurthy, Alekh Agarwal, Miro Dudík
Advances in Neural Information Processing Systems | December 2016
-
Minimax Structured Normal Means Inference
IEEE International Symposium on Information Theory | July 2016
-
Efficient Algorithms for Adversarial Contextual Learning
Vasilis Syrgkanis, Akshay Krishnamurthy, Robert E. Schapire
International Conference on Machine Learning | June 2016
-
Nonparametric von Mises estimators for entropies, divergences, and mutual informations
Kirthevasan Kandasamy, Akshay Krishnamurthy, Barnabas Poczos, Larry Wasserman, James M. Robins
Advances in Neural Information Processing Systems | December 2015
-
Learning to Search Better than Your Teacher
Kai-Wei Chang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Hal Daumé III
International Conference on Machine Learning | July 2015
-
On Estimating L_2^2 Divergence
Akshay Krishnamurthy, Kirthevasan Kandasamy, Barnabas Poczos, Larry Wasserman
Artificial Intelligence and Statistics | May 2015
-
Subspace learning from extremely compressed measurements
Akshay Krishnamurthy, Martin Azizyan, Aarti Singh
Asilomar Conference on Signals, Systems, and Computers | November 2014
-
Nonparametric Estimation of Renyi Divergence and Friends
Akshay Krishnamurthy, Kirthevasan Kandasamy, Barnabas Poczos, Larry Wasserman
International Conference on Machine Learning | July 2014
-
Near-optimal anomaly detection in graphs using Lovasz extended scan statistic
James Sharpnack, Akshay Krishnamurthy, Aarti Singh
Advances in Neural Information Processing Systems | December 2013
-
Low-Rank Matrix and Tensor Completion via Adaptive Sampling
Akshay Krishnamurthy, Aarti Singh
Advances in Neural Information Processing Systems | December 2013
-
Recovering graph-structured activations using adaptive compressive measurements
Akshay Krishnamurthy (akshaykr), James Sharpnack, Aarti Singh
Asilomar Conference on Signals, Systems, and Computers | November 2013
-
Detecting activations over graphs using spanning tree wavelet bases
James Sharpnack, Akshay Krishnamurthy, Aarti Singh
Artificial Intelligence and Statistics | April 2013
-
Completion of high-rank ultrametric matrices using selective entries
Aarti Singh, Akshay Krishnamurthy, Sivaraman Balakrishnan, Min Xu
International Conference on Signal Processing and Communication | July 2012
-
Efficient active algorithms for hierarchical clustering
Akshay Krishnamurthy, Sivaraman Balakrishnan, Min Xu, Aarti Singh
International Conference on Machine Learning | June 2012
-
Robust multi-source network tomography using selective probes
Akshay Krishnamurthy, Aarti Singh
IEEE Infocom | March 2012
-
Noise Thresholds for Spectral Clustering
Sivaraman Balakrishnan, Min Xu, Akshay Krishnamurthy, Aarti Singh
Advances in Neural Information Processing Systems | December 2011
-
-
-
TailSFT: Filtered Fine-Tuning Improves Post-Training Performance
Sadhika Malladi, Samy Jelassi, Dylan Foster, Jordan Ash, Akshay Krishnamurthy
August 2026
arXiv | August 2026
-
Learning to Reason with Curriculum II: Compositional Generalization
Nived Rajaraman, Audrey Huang, Miro Dudík, Robert E. Schapire, Dylan Foster, Akshay Krishnamurthy
June 2026
arXiv | June 2026
-
Select and Improve: Understanding the Mechanics of Post-Training for Reasoning
Akshay Krishnamurthy, Audrey Huang, Nived Rajaraman
June 2026
arXiv | June 2026
-
Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
Noah Golowich, Fan Chen, Dhruv Rohatgi, Raghav Singhal, Carles Domingo-Enrich, Dylan Foster, Akshay Krishnamurthy
March 2026
arXiv | March 2026
-
Next-Latent Prediction Transformers Learn Compact World Models
Jayden Teoh, Manan Tomar, Kwangjun Ahn, Edward J. Hu, Tim Pearce, Pratyusha Sharma, Akshay Krishnamurthy, Riashat Islam, Alex Lamb, John Langford
November 2025
arXiv | November 2025
-
Contrastive learning, multi-view redundancy, and linear models
Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
August 2020
ArXiv preprint | August 2020
-
Contrastive Estimation Reveals Topic Posterior Information To Linear Models
Christopher Tosh, Akshay Krishnamurthy, Daniel Hsu
March 2020
ArXiv | March 2020
-
Model-Based Reinforcement Learning in Contextual Decision Processes
Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford
November 2018
November 2018
-
-
-
Corrupted Multidimensional Binary Search: Learning In The Presence Of Irrational Agents
Akshay Krishnamurthy, Thodoris Lykouris, Chara Podimata
arXiv preprint arXiv:2002.11650 | February 2020
-
Active Learning for Cost-Sensitive Classification
Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang, John Langford, Hal Daumé III
Journal of Machine Learning Research | April 2019
-
Extreme compressive sampling for covariance estimation
Martin Azizyan, Akshay Krishnamurthy, Aarti Singh
IEEE Transactions on Information Theory | December 2018
-