Ayush Sekhari

19

Papers

48

Total Citations

Papers (19)

Machine Unlearning Fails to Remove Data Poisoning Attacks

Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees

GaussMark: A Practical Approach for Structural Watermarking of Language Models

Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics

The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches

NeurIPS 2025arXiv

Random Latent Exploration for Deep Reinforcement Learning

Reinforcement Learning with Feedback Graphs

NeurIPS 2020arXiv

Neural Active Learning with Performance Guarantees

Remember What You Want to Forget: Algorithms for Machine Unlearning

NeurIPS 2021arXiv

Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations

SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs

NeurIPS 2021arXiv

Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems

NeurIPS 2022arXiv

From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent

NeurIPS 2022arXiv

On the Complexity of Adversarial Decision Making

NeurIPS 2022arXiv

Contextual Bandits and Imitation Learning with Preference-Based Active Queries

NeurIPS 2023arXiv

Model-Free Reinforcement Learning with the Decision-Estimation Coefficient

NeurIPS 2023arXiv

When is Agnostic Reinforcement Learning Statistically Tractable?

NeurIPS 2023arXiv

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks

NeurIPS 2023arXiv

Selective Sampling and Imitation Learning via Online Regression

NeurIPS 2023arXiv