Picture for Karthik Sridharan

Karthik Sridharan

University of Pennsylvania

From Optimization to Sampling via Lyapunov Potentials

Add code
Oct 03, 2024
Viaarxiv icon

Langevin Dynamics: A Unified Perspective on Optimization via Lyapunov Potentials

Add code
Jul 05, 2024
Viaarxiv icon

Online Learning with Unknown Constraints

Add code
Mar 06, 2024
Viaarxiv icon

Contextual Bandits and Imitation Learning via Preference-Based Active Queries

Add code
Jul 24, 2023
Viaarxiv icon

Selective Sampling and Imitation Learning via Online Regression

Add code
Jul 11, 2023
Viaarxiv icon

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

Add code
Oct 13, 2022
Viaarxiv icon

On the Complexity of Adversarial Decision Making

Add code
Jun 27, 2022
Viaarxiv icon

Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation

Add code
Jun 19, 2022
Figure 1 for Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
Figure 2 for Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
Figure 3 for Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
Viaarxiv icon

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

Add code
Jul 11, 2021
Figure 1 for SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs
Figure 2 for SGD: The Role of Implicit Regularization, Batch-size and Multiple-epochs
Viaarxiv icon

Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations

Add code
Jun 22, 2021
Figure 1 for Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations
Figure 2 for Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations
Viaarxiv icon