Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent

Lampros Flokas
Lampros Flokas
Emmanouil-Vasileios Vlatakis-Gkaragkounis
Emmanouil-Vasileios Vlatakis-Gkaragkounis
Cited by: 0|Views4

Abstract:

Many recent AI architectures are inspired by zero-sum games, however, the behavior of their dynamics is still not well understood. Inspired by this, we study standard gradient descent ascent (GDA) dynamics in a specific class of non-convex non-concave zero-sum games, that we call hidden zero-sum games. In this class, players control the...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments