Ayush Sekhari

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 51

Top Topics

Function Approximation

Reinforcement Learning

Selective Sampling

Top Venues

Publications

Runzhe Wu, Ayush Sekhari, Akshay Krishnamurthy, Wen Sun
Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics. CoRR (2024)
Philip Amortila, Dylan J. Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie
Harnessing Density Ratios for Online Reinforcement Learning. CoRR (2024)
August Y. Chen, Ayush Sekhari, Karthik Sridharan
Langevin Dynamics: A Unified Perspective on Optimization via Lyapunov Potentials. CoRR (2024)
Yifei Zhou, Ayush Sekhari, Yuda Song, Wen Sun
Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees. ICLR (2024)
Zeyu Jia, Alexander Rakhlin, Ayush Sekhari, Chen-Yu Wei
Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data. COLT (2024)
Srinath Mahankali, Zhang-Wei Hong, Ayush Sekhari, Alexander Rakhlin, Pulkit Agrawal
Random Latent Exploration for Deep Reinforcement Learning. CoRR (2024)
Martin Pawelczyk, Jimmy Z. Di, Yiwei Lu, Gautam Kamath, Ayush Sekhari, Seth Neel
Machine Unlearning Fails to Remove Data Poisoning Attacks. CoRR (2024)
Philip Amortila, Dylan J. Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie
Harnessing Density Ratios for Online Reinforcement Learning. ICLR (2024)
Zeyu Jia, Alexander Rakhlin, Ayush Sekhari, Chen-Yu Wei
Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data. CoRR (2024)
Ayush Sekhari, Karthik Sridharan, Wen Sun, Runzhe Wu
Contextual Bandits and Imitation Learning via Preference-Based Active Queries. CoRR (2023)
Ayush Sekhari, Karthik Sridharan, Wen Sun, Runzhe Wu
Contextual Bandits and Imitation Learning with Preference-Based Active Queries. NeurIPS (2023)
Jimmy Z. Di, Jack Douglas, Jayadev Acharya, Gautam Kamath, Ayush Sekhari
Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks. NeurIPS (2023)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Ayush Sekhari, Chiyuan Zhang
Ticketed Learning-Unlearning Schemes. COLT (2023)
Ayush Sekhari, Karthik Sridharan, Wen Sun, Runzhe Wu
Selective Sampling and Imitation Learning via Online Regression. CoRR (2023)
Zeyu Jia, Gene Li, Alexander Rakhlin, Ayush Sekhari, Nati Srebro
When is Agnostic Reinforcement Learning Statistically Tractable? NeurIPS (2023)
Ayush Sekhari, Karthik Sridharan, Wen Sun, Runzhe Wu
Selective Sampling and Imitation Learning via Online Regression. NeurIPS (2023)
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Ayush Sekhari, Chiyuan Zhang
Ticketed Learning-Unlearning Schemes. CoRR (2023)
Yuda Song, Yifei Zhou, Ayush Sekhari, Drew Bagnell, Akshay Krishnamurthy, Wen Sun
Hybrid RL: Using both offline and online data can make RL efficient. ICLR (2023)
Dylan J. Foster, Noah Golowich, Jian Qian, Alexander Rakhlin, Ayush Sekhari
Model-Free Reinforcement Learning with the Decision-Estimation Coefficient. NeurIPS (2023)
Yifei Zhou, Ayush Sekhari, Yuda Song, Wen Sun
Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees. CoRR (2023)
Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun
Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings. ICML (2023)
Zeyu Jia, Gene Li, Alexander Rakhlin, Ayush Sekhari, Nathan Srebro
When is Agnostic Reinforcement Learning Statistically Tractable? CoRR (2023)
Dylan J. Foster, Noah Golowich, Jian Qian, Alexander Rakhlin, Ayush Sekhari
A Note on Model-Free Reinforcement Learning with the Decision-Estimation Coefficient. CoRR (2022)
Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan
Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation. CoRR (2022)
Dylan J. Foster, Alexander Rakhlin, Ayush Sekhari, Karthik Sridharan
On the Complexity of Adversarial Decision Making. CoRR (2022)
Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan
Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation. ICML (2022)
Satyen Kale, Jason D. Lee, Chris De Sa, Ayush Sekhari, Karthik Sridharan
From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent. CoRR (2022)
Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun
Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings. CoRR (2022)
Dylan J. Foster, Alexander Rakhlin, Ayush Sekhari, Karthik Sridharan
On the Complexity of Adversarial Decision Making. NeurIPS (2022)
Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun
Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems. NeurIPS (2022)
Yuda Song, Yifei Zhou, Ayush Sekhari, J. Andrew Bagnell, Akshay Krishnamurthy, Wen Sun
Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient. CoRR (2022)
Jimmy Z. Di, Jack Douglas, Jayadev Acharya, Gautam Kamath, Ayush Sekhari
Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks. CoRR (2022)
Christopher De Sa, Satyen Kale, Jason D. Lee, Ayush Sekhari, Karthik Sridharan
From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent. NeurIPS (2022)
Masatoshi Uehara, Ayush Sekhari, Jason D. Lee, Nathan Kallus, Wen Sun
Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems. CoRR (2022)
Ayush Sekhari, Karthik Sridharan, Satyen Kale
SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs. NeurIPS (2021)
Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan
Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations. CoRR (2021)
Ayush Sekhari, Christoph Dann, Mehryar Mohri, Yishay Mansour, Karthik Sridharan
Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations. NeurIPS (2021)
Zhilei Wang, Pranjal Awasthi, Christoph Dann, Ayush Sekhari, Claudio Gentile
Neural Active Learning with Performance Guarantees. NeurIPS (2021)
Ayush Sekhari, Jayadev Acharya, Gautam Kamath, Ananda Theertha Suresh
Remember What You Want to Forget: Algorithms for Machine Unlearning. CoRR (2021)
Ayush Sekhari, Jayadev Acharya, Gautam Kamath, Ananda Theertha Suresh
Remember What You Want to Forget: Algorithms for Machine Unlearning. NeurIPS (2021)
Satyen Kale, Ayush Sekhari, Karthik Sridharan
SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs. CoRR (2021)
Pranjal Awasthi, Christoph Dann, Claudio Gentile, Ayush Sekhari, Zhilei Wang
Neural Active Learning with Performance Guarantees. CoRR (2021)
Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan
Reinforcement Learning with Feedback Graphs. CoRR (2020)
Christoph Dann, Yishay Mansour, Mehryar Mohri, Ayush Sekhari, Karthik Sridharan
Reinforcement Learning with Feedback Graphs. NeurIPS (2020)
Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan J. Foster, Ayush Sekhari, Karthik Sridharan
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations. COLT (2020)
Yossi Arjevani, Yair Carmon, John C. Duchi, Dylan J. Foster, Ayush Sekhari, Karthik Sridharan
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations. CoRR (2020)
Dylan J. Foster, Ayush Sekhari, Ohad Shamir, Nathan Srebro, Karthik Sridharan, Blake E. Woodworth
The Complexity of Making the Gradient Small in Stochastic Convex Optimization. COLT (2019)
Dylan J. Foster, Ayush Sekhari, Ohad Shamir, Nathan Srebro, Karthik Sridharan, Blake E. Woodworth
The Complexity of Making the Gradient Small in Stochastic Convex Optimization. CoRR (2019)
Dylan J. Foster, Ayush Sekhari, Karthik Sridharan
Uniform Convergence of Gradients for Non-Convex Learning and Optimization. NeurIPS (2018)
Dylan J. Foster, Ayush Sekhari, Karthik Sridharan
Uniform Convergence of Gradients for Non-Convex Learning and Optimization. CoRR (2018)
Marc Pickett, Ayush Sekhari, James Davidson
A Brief Study of In-Domain Transfer and Learning from Fewer Samples using A Few Simple Priors. CoRR (2017)