Smooth markets: A basic mechanism for organizing gradient-based learners

Balduzzi, David, Czarnecki, Wojciech M, Anthony, Thomas W, Gemp, Ian M, Hughes, Edward, Leibo, Joel Z, Piliouras, Georgios, Graepel, Thore

arXiv.org Artificial Intelligence 

With the success of modern machine learning, it is becoming increasingly important to understand and control how learning algorithms interact. Unfortunately, negative results from game theory show there is little hope of understanding or controlling general n-player games. We therefore introduce smooth markets (SM-games), a class of n-player games with pairwise zero sum interactions. SM-games codify a common design pattern in machine learning that includes (some) GANs, adversarial training, and other recent algorithms. We show that SM-games are amenable to analysis and optimization using first-order methods.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found