James P. Bailey

activity

20192026

most citedFinite Regret and Cycles with Fixed Step-Size via Alternating Gradient Descent-Ascent

7 citations · 14 across the 7 of their papers we have counts for

collaborators

Showing 2021Show all

3 papers · 1 filter

cs.GT2021

$O (1/ T)$ Time-Average Convergence in a Generalization of Multiagent Zero-Sum Games

James P. Bailey

We introduce a generalization of zero-sum network multiagent matrix games and prove that alternating gradient descent converges to the set of Nash equilibria at rate $O (1/ T)$ for t…

cs.GT2021★ 1 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…

cs.GT2021

Conditions for Stability in Strategic Matching

James P. Bailey, Craig A. Tovey

We consider the stability of matchings when individuals strategically submit preference information to a publicly known algorithm. Most pure Nash equilibria of the ensuing game yie…

O(1/T) Time-Average Convergence in a Generalization of Multiagent Zero-Sum Games

Stochastic Multiplicative Weights Updates in Zero-Sum Games

Conditions for Stability in Strategic Matching

$O (1/ T)$ Time-Average Convergence in a Generalization of Multiagent Zero-Sum Games