Picture for Sarath Pattathil

Sarath Pattathil

Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing Dynamics

Add code
Jan 30, 2023
Figure 1 for Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing Dynamics
Figure 2 for Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing Dynamics
Figure 3 for Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing Dynamics
Figure 4 for Autobidders with Budget and ROI Constraints: Efficiency, Regret, and Pacing Dynamics
Viaarxiv icon

Revisiting the Linear-Programming Framework for Offline RL with General Function Approximation

Add code
Dec 28, 2022
Viaarxiv icon

Symmetric (Optimistic) Natural Policy Gradient for Multi-agent Learning with Parameter Convergence

Add code
Oct 23, 2022
Viaarxiv icon

What is a Good Metric to Study Generalization of Minimax Learners?

Add code
Jun 20, 2022
Figure 1 for What is a Good Metric to Study Generalization of Minimax Learners?
Figure 2 for What is a Good Metric to Study Generalization of Minimax Learners?
Figure 3 for What is a Good Metric to Study Generalization of Minimax Learners?
Viaarxiv icon

Tight last-iterate convergence rates for no-regret learning in multi-player games

Add code
Oct 26, 2020
Figure 1 for Tight last-iterate convergence rates for no-regret learning in multi-player games
Viaarxiv icon

An Optimal Multistage Stochastic Gradient Method for Minimax Problems

Add code
Feb 13, 2020
Figure 1 for An Optimal Multistage Stochastic Gradient Method for Minimax Problems
Viaarxiv icon

Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems

Add code
Jan 31, 2020
Viaarxiv icon

A Decentralized Proximal Point-type Method for Saddle Point Problems

Add code
Oct 31, 2019
Figure 1 for A Decentralized Proximal Point-type Method for Saddle Point Problems
Figure 2 for A Decentralized Proximal Point-type Method for Saddle Point Problems
Figure 3 for A Decentralized Proximal Point-type Method for Saddle Point Problems
Viaarxiv icon

Proximal Point Approximations Achieving a Convergence Rate of $\mathcal{O}(1/k)$ for Smooth Convex-Concave Saddle Point Problems: Optimistic Gradient and Extra-gradient Methods

Add code
Jun 03, 2019
Viaarxiv icon

A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach

Add code
Jan 24, 2019
Figure 1 for A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach
Figure 2 for A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach
Figure 3 for A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach
Figure 4 for A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach
Viaarxiv icon