Two Steps at a Time---Taking GAN Training in Stride with Tseng's Method
SIAM Journal on Mathematics of Data Science · 2022-06 · 4 (2) · 750-771
DOI: 10.1137/21m1420939 ↗Kurz gefasst
Fachartikel in der Zeitschrift SIAM Journal on Mathematics of Data Science, online erschienen am 23.06.2022. Verfasst von Axel Böhm und 3 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 55 Literaturangaben. Gefördert von: Vienna Graduate School on Computational Optimization, Austrian Science Fund.
Abstract (Originalsprache)
Motivated by the training of generative adversarial networks (GANs), we study methods for solving minimax problems with additional nonsmooth regularizers. We do so by employing monotone operator theory, in particular the forward-backward-forward method, which avoids the known issue of limit cycling by correcting each update by a second gradient evaluation and does so requiring fewer projection steps compared to the extragradient method in the presence of constraints. Furthermore, we propose a seemingly new scheme which recycles old gradients to mitigate the additional computational cost. In doing so we rediscover a known method, related to optimistic gradient descent ascent. For both schemes we prove novel convergence rates for convex-concave minimax problems via a unifying approach. The derived error bounds are in terms of the gap function for the ergodic iterates. For the deterministic and the stochastic problem we show a convergence rate of $\mathcal{O}({1}/{k})$ and $\mathcal{O}({1}/{\sqrt{k}})$, respectively. We complement our theoretical results with empirical improvements in the training of Wasserstein GANs on the CIFAR10 dataset.
Förderung
- Vienna Graduate School on Computational Optimization
- Austrian Science Fund
Zitieren
APA
Böhm, A., Sedlmayer, M., Csetnek, E. R., & Boţ, R. I. (2022). Two Steps at a Time---Taking GAN Training in Stride with Tseng's Method. SIAM Journal on Mathematics of Data Science, 4(2), 750-771. https://doi.org/10.1137/21m1420939
Vancouver
Böhm A, Sedlmayer M, Csetnek ER, Boţ RI. Two Steps at a Time---Taking GAN Training in Stride with Tseng's Method. SIAM Journal on Mathematics of Data Science. 2022;4(2):750-771. doi:10.1137/21m1420939
BibTeX
@article{Bhm2022,
author = {Böhm, Axel and Sedlmayer, Michael and Csetnek, Ernö Robert and Boţ, Radu Ioan},
title = {Two Steps at a Time---Taking GAN Training in Stride with Tseng's Method},
journal = {SIAM Journal on Mathematics of Data Science},
year = {2022},
volume = {4},
number = {2},
pages = {750--771},
doi = {10.1137/21m1420939}
}
EUVIMED