提升游戏动力学的负动量

Jul, 2018

Negative Momentum for Improved Game Dynamics

Gauthier Gidel, Reyhane Askari Hemmat, Mohammad Pezeshki, Gabriel Huang, Remi Lepriol...

TL;DR本文分析了基于动量的梯度下降法在线性游戏中的应用，证明交替更新比同时更新更加稳定。同时，理论和实验都表明带有负动量项的交替梯度下降法能够实现在困难的攻击问题和难以训练的 saturating GANs 中的收敛。

Abstract

Games generalize the optimization paradigm by introducing different objective functions for different optimizing agents, known as players. generative adversarial networks (GANs) are arguably the most popular game formulation in recent →