← Authors

Ayush Sekhari

30 papers · 2018–2025 · 4 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (4) πŸƒ Academic Marathon (7) 🌈 Renaissance Researcher (7) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (29) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🀝 Dynamic Duo (12) πŸ”¬ Deep Specialist (12) πŸ‘‘ Triple Crown πŸ’Ž Century Club (30) πŸ“ˆ Trend Setter πŸ—ƒοΈ Keyword Collector (89) πŸ”₯ Unstoppable (8) ❓ The Questioner ⚑ Prolific Year (6)

Conferences

NIPS (14) COLT (6) ICLR (5) ICML (5)

Top co-authors

Karthik Sridharan (12) Wen Sun (7) Alexander Rakhlin (6) Dylan J Foster (4) Runzhe Wu (3) Gautam Kamath (3) Christoph Dann (3) Akshay Krishnamurthy (3) Mehryar Mohri (3) Yishay Mansour (3)

Research topics

Privacy (1)

Keywords

sample complexity (6) reinforcement learning (5) regret bound (5) policy learning (3) machine unlearning (3) function approximation (3) active learning (2) stochastic gradient descent (2) non-convex optimization (2) imitation learning (2) stationary point (2) oracle complexity (2) partially observable markov decision process (2) agnostic learning (2) stochastic convex optimization (2) convergence analysis (1) convex optimization (1) offline reinforcement learning (1) recursive regularization (1) data poisoning (1)

Papers

Machine Unlearning Fails to Remove Data Poisoning Attacks ICLR 2025
Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics ICLR 2025
System-Aware Unlearning Algorithms: Use Lesser, Forget Faster ICML 2025
GaussMark: A Practical Approach for Structural Watermarking of Language Models ICML 2025
The Role of Environment Access in Agnostic Reinforcement Learning (Extended Abstract) COLT 2025
The Space Complexity of Learning-Unlearning Algorithms (extended abstract) COLT 2025
Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees ICLR 2024
Harnessing Density Ratios for Online Reinforcement Learning ICLR 2024
Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data COLT 2024
Random Latent Exploration for Deep Reinforcement Learning ICML 2024
Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings ICML 2023
Contextual Bandits and Imitation Learning with Preference-Based Active Queries NIPS 2023
Model-Free Reinforcement Learning with the Decision-Estimation Coefficient NIPS 2023
When is Agnostic Reinforcement Learning Statistically Tractable? NIPS 2023
Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks NIPS 2023
Selective Sampling and Imitation Learning via Online Regression NIPS 2023
Ticketed Learning–Unlearning Schemes COLT 2023
Hybrid RL: Using both offline and online data can make RL efficient ICLR 2023
From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent NIPS 2022
Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems NIPS 2022
Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation ICML 2022
On the Complexity of Adversarial Decision Making NIPS 2022
Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations NIPS 2021
Remember What You Want to Forget: Algorithms for Machine Unlearning NIPS 2021
Neural Active Learning with Performance Guarantees NIPS 2021
SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs NIPS 2021
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations COLT 2020
Reinforcement Learning with Feedback Graphs NIPS 2020
The Complexity of Making the Gradient Small in Stochastic Convex Optimization COLT 2019
Uniform Convergence of Gradients for Non-Convex Learning and Optimization NIPS 2018