v1v2 (latest)

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

31 January 2020

Asuman Ozdaglar

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

50 / 56 papers shown

Title
Negative Stepsizes Make Gradient-Descent-Ascent Converge Henry Shugart Jason M. Altschuler 110 1 0 02 May 2025
Learning Variational Inequalities from Data: Fast Generalization Rates under Strong Monotonicity Eric Zhao Tatjana Chavdarova Michael I. Jordan 139 0 0 20 Feb 2025
Constrained Sampling with Primal-Dual Langevin Monte Carlo Luiz F. O. Chamon Mohammad Reza Karimi Anna Korba 159 5 0 08 Jan 2025
COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences Yongxu Liu Argyris Oikonomou Weiqiang Zheng Yang Cai Arman Cohan 137 1 0 30 Oct 2024
Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms Yang Cai Gabriele Farina Julien Grand-Clément Christian Kroer Chung-Wei Lee Haipeng Luo Weiqiang Zheng 161 8 0 15 Jun 2024
Primal Methods for Variational Inequality Problems with Functional Constraints Liang Zhang Niao He Michael Muehlebach 151 3 0 19 Mar 2024
Diffusion Stochastic Optimization for Min-Max Problems H. Cai Sulaiman A. Alghunaim Ali H. Sayed 105 3 0 26 Jan 2024
Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence Beyond the Minty Property Ioannis Anagnostides Ioannis Panageas Gabriele Farina Tuomas Sandholm 158 3 0 19 Dec 2023
Last-Iterate Convergence Properties of Regret-Matching Algorithms in Games Yang Cai Gabriele Farina Julien Grand-Clément Christian Kroer Chung-Wei Lee Haipeng Luo Weiqiang Zheng 143 4 0 01 Nov 2023
A Specialized Semismooth Newton Method for Kernel-Based Optimal Transport Tianyi Lin Marco Cuturi Michael I. Jordan OT 108 0 0 21 Oct 2023
Stable Nonconvex-Nonconcave Training via Linear Interpolation Thomas Pethick Wanyun Xie Volkan Cevher 138 6 0 20 Oct 2023
Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions Xu Cai Ahmet Alacaoglu Jelena Diakonikolas 148 9 0 04 Oct 2023
Extragradient Type Methods for Riemannian Variational Inequality Problems Zihao Hu Guanghui Wang Xi Wang Andre Wibisono Jacob D. Abernethy Molei Tao 107 4 0 25 Sep 2023
Curvature-Independent Last-Iterate Convergence for Games on Riemannian Manifolds Yong Cai Michael I. Jordan Tianyi Lin Argyris Oikonomou Emmanouil-Vasileios Vlatakis-Gkaragkounis 102 4 0 29 Jun 2023
A Central Limit Theorem for Algorithmic Estimator of Saddle Point Abhishek Roy Yian Ma 135 1 0 09 Jun 2023
Adaptively Perturbed Mirror Descent for Learning in Games Kenshi Abe Kaito Ariu Mitsuki Sakamoto Atsushi Iwasaki 159 6 0 26 May 2023
Accelerating Value Iteration with Anchoring Jongmin Lee Ernest K. Ryu 75 10 0 26 May 2023
Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games Hédi Hadiji Sarah Sachs T. Erven Wouter M. Koolen 136 5 0 25 Apr 2023
Sublinear Convergence Rates of Extragradient-Type Methods: A Survey on Classical and Recent Developments Quoc Tran-Dinh 96 8 0 30 Mar 2023
Doubly Optimal No-Regret Learning in Monotone Games Yang Cai Weiqiang Zheng 159 14 0 30 Jan 2023
ApproxED: Approximate exploitability descent via learned best responses Carlos Martin Tuomas Sandholm 138 0 0 20 Jan 2023
Min-Max Optimization Made Simple: Approximating the Proximal Point Method via Contraction Maps Volkan Cevher Georgios Piliouras Ryann Sim Stratis Skoulakis 119 6 0 10 Jan 2023
Symmetric (Optimistic) Natural Policy Gradient for Multi-agent Learning with Parameter Convergence S. Pattathil Jianchao Tan Asuman Ozdaglar 145 14 0 23 Oct 2022
STay-ON-the-Ridge: Guaranteed Convergence to Local Minimax Equilibrium in Nonconvex-Nonconcave Games C. Daskalakis Noah Golowich Stratis Skoulakis Manolis Zampetakis 157 7 0 18 Oct 2022
Last-Iterate Convergence with Full and Noisy Feedback in Two-Player Zero-Sum Games Kenshi Abe Kaito Ariu Mitsuki Sakamoto Kenta Toyoshima Atsushi Iwasaki 124 14 0 21 Aug 2022
A Survey of Decision Making in Adversarial Games Xiuxian Li Min Meng Yiguang Hong Jie-bin Chen AAML 121 16 0 16 Jul 2022
Continuous-time Analysis for Variational Inequalities: An Overview and Desiderata Tatjana Chavdarova Ya-Ping Hsieh Michael I. Jordan 76 2 0 14 Jul 2022
Solving Constrained Variational Inequalities via a First-order Interior Point-based Method Tong Yang Michael I. Jordan Tatjana Chavdarova 122 10 0 21 Jun 2022
Accelerated Algorithms for Constrained Nonconvex-Nonconcave Min-Max Optimization and Comonotone Inclusion Yang Cai Argyris Oikonomou Weiqiang Zheng 186 22 0 10 Jun 2022
What is a Good Metric to Study Generalization of Minimax Learners? Asuman Ozdaglar S. Pattathil Jiawei Zhang Jianchao Tan 97 14 0 09 Jun 2022
Policy Optimization for Markov Games: Unified Framework and Faster Convergence Runyu Zhang Qinghua Liu Haiquan Wang Caiming Xiong Na Li Yu Bai 154 29 0 06 Jun 2022
First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces Michael I. Jordan Tianyi Lin Emmanouil-Vasileios Vlatakis-Gkaragkounis 123 19 0 04 Jun 2022
Tight Last-Iterate Convergence of the Extragradient and the Optimistic Gradient Descent-Ascent Algorithm for Constrained Monotone Variational Inequalities Yang Cai Argyris Oikonomou Weiqiang Zheng 115 16 0 20 Apr 2022
Stochastic Halpern Iteration with Variance Reduction for Stochastic Monotone Inclusions Xu Cai Chaobing Song Cristóbal Guzmán Jelena Diakonikolas 169 11 0 17 Mar 2022
Last-Iterate Convergence of Saddle-Point Optimizers via High-Resolution Differential Equations Tatjana Chavdarova Michael I. Jordan Manolis Zampetakis 182 16 0 27 Dec 2021
Convergence Rates of Two-Time-Scale Gradient Descent-Ascent Dynamics for Solving Nonconvex Min-Max Problems Thinh T. Doan 157 17 0 17 Dec 2021
Doubly Optimal No-Regret Online Learning in Strongly Monotone Games with Bandit Feedback Wenjia Ba Tianyi Lin Jiawei Zhang Zhengyuan Zhou 113 12 0 06 Dec 2021
Stochastic Extragradient: General Analysis and Improved Rates Eduard A. Gorbunov Hugo Berard Gauthier Gidel Nicolas Loizou 100 44 0 16 Nov 2021
Extragradient Method: $O(1/K)$ Last-Iterate Convergence for Monotone Variational Inequalities and Connections With Cocoercivity Eduard A. Gorbunov Nicolas Loizou Gauthier Gidel 157 68 0 08 Oct 2021
Nonconvex-Nonconcave Min-Max Optimization with a Small Maximization Domain Dmitrii Ostrovskii Babak Barazandeh Meisam Razaviyayn 115 13 0 08 Oct 2021
$$O\left(1/T\right)$ Time-Average Convergence in a Generalization of Multiagent Zero-Sum Games$ $O\left(1/T\right)$ Time-Average Convergence in a Generalization of Multiagent Zero-Sum Games James P. Bailey 55 0 0 06 Oct 2021
Fair Representation: Guaranteeing Approximate Multiple Group Fairness for Unknown Tasks Xudong Shen Yongkang Wong Mohan S. Kankanhalli FaML 131 22 0 01 Sep 2021
The Last-Iterate Convergence Rate of Optimistic Mirror Descent in Stochastic Variational Inequalities Waïss Azizian F. Iutzeler J. Malick P. Mertikopoulos 101 29 0 05 Jul 2021
Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity Nicolas Loizou Hugo Berard Gauthier Gidel Ioannis Mitliagkas Simon Lacoste-Julien 149 55 0 30 Jun 2021
On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging C. J. Li Yaodong Yu Nicolas Loizou Gauthier Gidel Yi-An Ma Nicolas Le Roux Michael I. Jordan 155 25 0 30 Jun 2021
Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization Haochuan Li Yi Tian Jingzhao Zhang Ali Jadbabaie 117 42 0 18 Apr 2021
On the Initialization for Convex-Concave Min-max Problems Mingrui Liu Francesco Orabona ODL 76 4 0 27 Feb 2021
Stochastic Variance Reduction for Variational Inequality Methods Ahmet Alacaoglu Yura Malitsky 139 74 0 16 Feb 2021
Potential Function-based Framework for Making the Gradients Small in Convex and Min-Max Optimization Jelena Diakonikolas Puqian Wang 91 13 0 28 Jan 2021
Independent Policy Gradient Methods for Competitive Reinforcement Learning C. Daskalakis Dylan J. Foster Noah Golowich 297 168 0 11 Jan 2021