Ayush Sekhari
30 papers · 2018–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
๐บ๏ธ Taxonomy Completionist (42) ๐ Academic Marathon ยท Sprint ๐ Conference Polyglot ยท Bronze ๐ Interdisciplinary Bridge ยท Silver ๐ฃ Hot Topic Early Bird
๐ค
Dynamic Duo
(12)
๐
Keyword Champion
(2)
๐
Triple Crown
๐ฌ
Deep Specialist
(15)
๐
Renaissance Researcher
(7)
๐ฅ
Unstoppable ยท Bronze
โ
The Questioner
โก
Prolific Year ยท Productive
๐
Century Club ยท Bronze
๐
Trend Setter
๐๏ธ
Keyword Collector
(138)
Venues
Top co-authors
Research topics
Machine Learning
(26)
Optimization & Theory
(18)
Reinforcement Learning
(11)
Learning Types
(11)
Methods
(10)
Artificial Intelligence
(9)
Core AI
(8)
Application Areas
(4)
Mathematics & Optimization
(3)
Applications
(3)
Optimization
(3)
Computer Science
(2)
Deep Learning
(2)
Core Methods
(2)
Learning Paradigms
(2)
Keywords
reinforcement learning
(7)
sample complexity
(6)
regret bound
(5)
function approximation
(4)
machine unlearning
(4)
policy learning
(3)
stochastic gradient descent
(2)
active learning
(2)
stationary point
(2)
data poisoning
(2)
non-convex optimization
(2)
imitation learning
(2)
oracle complexity
(2)
agnostic learning
(2)
offline reinforcement learning
(2)
markov decision process
(2)
partially observable markov decision process
(2)
selective sampling
(2)
stochastic convex optimization
(2)
hybrid reinforcement learning
(2)
Papers
Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics
ICLR 2025
GaussMark: A Practical Approach for Structural Watermarking of Language Models
ICML 2025
Machine Unlearning Fails to Remove Data Poisoning Attacks
ICLR 2025
System-Aware Unlearning Algorithms: Use Lesser, Forget Faster
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
Harnessing Density Ratios for Online Reinforcement Learning
ICLR 2024
Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
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
NeurIPS 2023
Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
NeurIPS 2023
Hybrid RL: Using both offline and online data can make RL efficient
ICLR 2023
Model-Free Reinforcement Learning with the Decision-Estimation Coefficient
NeurIPS 2023
Selective Sampling and Imitation Learning via Online Regression
NeurIPS 2023
Ticketed LearningโUnlearning Schemes
COLT 2023
When is Agnostic Reinforcement Learning Statistically Tractable?
NeurIPS 2023
From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent
NeurIPS 2022
Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
ICML 2022
On the Complexity of Adversarial Decision Making
NeurIPS 2022
Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems
NeurIPS 2022
Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations
NeurIPS 2021
Neural Active Learning with Performance Guarantees
NeurIPS 2021
Remember What You Want to Forget: Algorithms for Machine Unlearning
NeurIPS 2021
SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs
NeurIPS 2021
Reinforcement Learning with Feedback Graphs
NeurIPS 2020
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations
COLT 2020
The Complexity of Making the Gradient Small in Stochastic Convex Optimization
COLT 2019
Uniform Convergence of Gradients for Non-Convex Learning and Optimization
NeurIPS 2018