Two steps at a time --- taking GAN training in stride with Tseng's method

no code implementations • 1 Jan 2021 • Axel Böhm, Michael Sedlmayer, Ernö Robert Csetnek, Radu Ioan Bot

Motivated by the training of Generative Adversarial Networks (GANs), we study methods for solving minimax problems with additional nonsmooth regularizers.

Fast optimization via inertial dynamics with closed-loop damping

no code implementations • 5 Aug 2020 • Hedy Attouch, Radu Ioan Bot, Ernö Robert Csetnek

In a Hilbert space $H$, in order to develop fast optimization methods, we analyze the asymptotic behavior, as time $t$ tends to infinity, of inertial continuous dynamics where the damping acts as a closed-loop control.

Optimization and Control Dynamical Systems 37N40, 46N10, 49M30, 65K05, 65K10, 90B50, 90C25

A Relaxed Inertial Forward-Backward-Forward Algorithm for Solving Monotone Inclusions with Application to GANs

no code implementations • 17 Mar 2020 • Radu Ioan Bot, Michael Sedlmayer, Phan Tu Vuong

We introduce a relaxed inertial forward-backward-forward (RIFBF) splitting algorithm for approaching the set of zeros of the sum of a maximally monotone operator and a single-valued monotone and Lipschitz continuous operator.

Forward-backward-forward methods with variance reduction for stochastic variational inequalities

no code implementations • 9 Feb 2019 • Radu Ioan Bot, Panayotis Mertikopoulos, Mathias Staudigl, Phan Tu Vuong

We develop a new stochastic algorithm with variance reduction for solving pseudo-monotone stochastic variational inequalities.