Jérôme Malick

Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling

2020 · arXiv (Cornell University)

Owing to their stability and convergence speed, extragradient methods have become a staple for solving large-scale saddle-point problems in machine learning. The basic premise of these algorithms is the use of an extrapolation step before …