activity
20162022
most citedFirst-order Methods Almost Always Avoid Saddle Points

76 citations · 264 across the 37 of their papers we have counts for

collaborators

52 papers

cs.GT20221 cited

Nash, Conley, and Computation: Impossibility and Incompleteness in Game Dynamics

Jason Milionis, Christos Papadimitriou, Georgios Piliouras +1

Under what conditions do the behaviors of players, who play a game repeatedly, converge to a Nash equilibrium? If one assumes that the players' behavior is a discrete-time or conti…

cs.GT2022

No-Regret Learning in Games is Turing Complete

Gabriel P. Andrade, Rafael Frongillo, Georgios Piliouras

Games are natural models for multi-agent machine learning settings, such as generative adversarial networks (GANs). The desirable outcomes from algorithmic interactions in these ga…

cs.GT2022

Unpredictable dynamics in congestion games: memory loss can prevent chaos

Jakub Bielawski, Thiparat Chotibut, Fryderyk Falniowski +2

We study the dynamics of simple congestion games with two resources where a continuum of agents behaves according to a version of Experience-Weighted Attraction (EWA) algorithm. Th…

cs.LG20221 cited

Multi-agent Performative Prediction: From Global Stability and Optimality to Chaos

Georgios Piliouras, Fang-Yi Yu

The recent framework of performative prediction is aimed at capturing settings where predictions influence the target/outcome they want to predict. In this paper, we introduce a na…

cs.GT2021

Online Learning in Periodic Zero-Sum Games

Tanner Fiez, Ryann Sim, Stratis Skoulakis +2

A seminal result in game theory is von Neumann's minmax theorem, which states that zero-sum games admit an essentially unique equilibrium solution. Classical learning results build…

cs.GT20211 cited

Stochastic Multiplicative Weights Updates in Zero-Sum Games

James P. Bailey, Sai Ganesh Nagarajan, Georgios Piliouras

We study agents competing against each other in a repeated network zero-sum game while applying the multiplicative weights update (MWU) algorithm with fixed learning rates. In our…