Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Asuman Ozdaglar

A Wasserstein Minimax Framework for Mixed Linear Regression


Jun 16, 2021
Theo Diamandis, Yonina C. Eldar, Alireza Fallah, Farzan Farnia, Asuman Ozdaglar

* To appear in 38th International Conference on Machine Learning (ICML 2021) 

  Access Paper or Ask Questions

Decentralized Q-Learning in Zero-sum Markov Games


Jun 04, 2021
Muhammed O. Sayin, Kaiqing Zhang, David S. Leslie, Tamer Basar, Asuman Ozdaglar


  Access Paper or Ask Questions

Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks


Feb 07, 2021
Alireza Fallah, Aryan Mokhtari, Asuman Ozdaglar


  Access Paper or Ask Questions

Train simultaneously, generalize better: Stability of gradient-based minimax learners


Oct 23, 2020
Farzan Farnia, Asuman Ozdaglar


  Access Paper or Ask Questions

Multi-agent Bayesian Learning with Adaptive Strategies: Convergence and Stability


Oct 18, 2020
Manxi Wu, Saurabh Amin, Asuman Ozdaglar


  Access Paper or Ask Questions

Fictitious play in zero-sum stochastic games


Oct 12, 2020
Muhammed O. Sayin, Francesca Parise, Asuman Ozdaglar


  Access Paper or Ask Questions

GANs May Have No Nash Equilibria


Feb 21, 2020
Farzan Farnia, Asuman Ozdaglar


  Access Paper or Ask Questions

Personalized Federated Learning: A Meta-Learning Approach


Feb 19, 2020
Alireza Fallah, Aryan Mokhtari, Asuman Ozdaglar


  Access Paper or Ask Questions

An Optimal Multistage Stochastic Gradient Method for Minimax Problems


Feb 13, 2020
Alireza Fallah, Asuman Ozdaglar, Sarath Pattathil


  Access Paper or Ask Questions

Provably Convergent Policy Gradient Methods for Model-Agnostic Meta-Reinforcement Learning


Feb 12, 2020
Alireza Fallah, Aryan Mokhtari, Asuman Ozdaglar


  Access Paper or Ask Questions

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


Jan 31, 2020
Noah Golowich, Sarath Pattathil, Constantinos Daskalakis, Asuman Ozdaglar

* 25 pages 

  Access Paper or Ask Questions

Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks


Nov 15, 2019
Alireza Fallah, Mert Gurbuzbalaban, Asuman Ozdaglar, Umut Simsekli, Lingjiong Zhu


  Access Paper or Ask Questions

A Decentralized Proximal Point-type Method for Saddle Point Problems


Oct 31, 2019
Weijie Liu, Aryan Mokhtari, Asuman Ozdaglar, Sarath Pattathil, Zebang Shen, Nenggan Zheng

* 18 pages 

  Access Paper or Ask Questions

On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithms


Sep 25, 2019
Alireza Fallah, Aryan Mokhtari, Asuman Ozdaglar

* 33 pages 

  Access Paper or Ask Questions

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


Jun 03, 2019
Aryan Mokhtari, Asuman Ozdaglar, Sarath Pattathil

* 15 pages 

  Access Paper or Ask Questions

A Universally Optimal Multistage Accelerated Stochastic Gradient Method


Jan 25, 2019
Necdet Serhat Aybat, Alireza Fallah, Mert Gurbuzbalaban, Asuman Ozdaglar

* 20 pages, 12 figures 

  Access Paper or Ask Questions

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


Jan 24, 2019
Aryan Mokhtari, Asuman Ozdaglar, Sarath Pattathil

* 31 pages, 3 figures 

  Access Paper or Ask Questions

Escaping Saddle Points in Constrained Optimization


Oct 09, 2018
Aryan Mokhtari, Asuman Ozdaglar, Ali Jadbabaie


  Access Paper or Ask Questions

Convergence Rate of Block-Coordinate Maximization Burer-Monteiro Method for Solving Large SDPs


Jul 12, 2018
Murat A. Erdogdu, Asuman Ozdaglar, Pablo A. Parrilo, Nuri Denizcan Vanli


  Access Paper or Ask Questions

A Fast Distributed Proximal-Gradient Method


Oct 08, 2012
Annie I. Chen, Asuman Ozdaglar

* 10 pages (including 2-page appendix); 1 figure; submitted to Allerton 2012 on July 10, 2012; accepted by Allerton 2012, October 2012 

  Access Paper or Ask Questions