On the Impossibility of Global Convergence in Multi-Loss Optimization

26 May 2020

Papers citing "On the Impossibility of Global Convergence in Multi-Loss Optimization"

19 / 19 papers shown

Title
Analysing the Sample Complexity of Opponent Shaping Kitty Fung Qizhen Zhang Chris Xiaoxuan Lu Jia Wan Timon Willi Jakob N. Foerster 26 0 0 08 Feb 2024
The Danger Of Arrogance: Welfare Equilibra As A Solution To Stackelberg Self-Play In Non-Coincidental Games Jake Levi Chris Xiaoxuan Lu Timon Willi Christian Schroeder de Witt Jakob N. Foerster 28 0 0 02 Feb 2024
Exploiting hidden structures in non-convex games for convergence to Nash equilibrium Iosif Sakos Emmanouil-Vasileios Vlatakis-Gkaragkounis P. Mertikopoulos Georgios Piliouras 14 4 0 27 Dec 2023
Chaos persists in large-scale multi-agent learning despite adaptive learning rates Emmanouil-Vasileios Vlatakis-Gkaragkounis Lampros Flokas Georgios Piliouras 10 1 0 01 Jun 2023
Alternating Mirror Descent for Constrained Min-Max Games Andre Wibisono Molei Tao Georgios Piliouras 24 14 0 08 Jun 2022
Competitive Gradient Optimization Abhijeet Vyas Kamyar Azizzadenesheli 6 1 0 27 May 2022
Nash, Conley, and Computation: Impossibility and Incompleteness in Game Dynamics Jason Milionis Christos H. Papadimitriou Georgios Piliouras Kelly Spendlove 11 9 0 26 Mar 2022
No-Regret Learning in Games is Turing Complete Gabriel P. Andrade Rafael M. Frongillo Georgios Piliouras 11 7 0 24 Feb 2022
Multi-agent Performative Prediction: From Global Stability and Optimality to Chaos Georgios Piliouras Fang-Yi Yu 40 34 0 25 Jan 2022
Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity Junchi Yang Antonio Orvieto Aurelien Lucchi Niao He 24 62 0 10 Dec 2021
Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective Junzhe Zhang Haochuan Li S. Sra Ali Jadbabaie 66 9 0 12 Oct 2021
Constants of Motion: The Antidote to Chaos in Optimization and Game Dynamics Georgios Piliouras Xiao Wang 26 0 0 08 Sep 2021
A Game-Theoretic Approach to Multi-Agent Trust Region Optimization Ying Wen Hui Chen Yaodong Yang Zheng Tian Minne Li Xu Chen Jun Wang 38 11 0 12 Jun 2021
Minimax Optimization with Smooth Algorithmic Adversaries Tanner Fiez Chi Jin Praneeth Netrapalli Lillian J. Ratliff AAML 16 11 0 02 Jun 2021
Learning in Matrix Games can be Arbitrarily Complex Gabriel P. Andrade Rafael M. Frongillo Georgios Piliouras 15 31 0 05 Mar 2021
ScrofaZero: Mastering Trick-taking Poker Game Gongzhu by Deep Reinforcement Learning Naichen Shi Ruichen Li Sun Youran 11 0 0 15 Feb 2021
Limiting Behaviors of Nonconvex-Nonconcave Minimax Optimization via Continuous-Time Systems Benjamin Grimmer Haihao Lu Pratik Worah Vahab Mirrokni 26 7 0 20 Oct 2020
The limits of min-max optimization algorithms: convergence to spurious non-critical sets Ya-Ping Hsieh P. Mertikopoulos V. Cevher 27 81 0 16 Jun 2020
First-order Methods Almost Always Avoid Saddle Points J. Lee Ioannis Panageas Georgios Piliouras Max Simchowitz Michael I. Jordan Benjamin Recht ODL 93 82 0 20 Oct 2017