Titel
A Relaxed Inertial Forward-Backward-Forward Algorithm for Solving Monotone Inclusions with Application to GANs
Autor*in
Tu Vuong Phan
Mathematical Sciences, University of Southampton
Abstract
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. This work aims to extend Tseng's forward-backward-forward method by both using inertial effects as well as relaxation parameters. We formulate first a second order dynamical system that approaches the solution set of the monotone inclusion problem to be solved and provide an asymptotic analysis for its trajectories. We provide for RIFBF, which follows by explicit time discretization, a convergence analysis in the general monotone case as well as when applied to the solving of pseudo-monotone variational inequalities. We illustrate the proposed method by applications to a bilinear saddle point problem, in the context of which we also emphasize the interplay between the inertial and the relaxation parameters, and to the training of Generative Adversarial Networks (GANs).
Stichwort
forward-backward-forward algorithminertial effectsrelaxation parameterscontinuous time approachapplication to GANs
Objekt-Typ
Sprache
Englisch [eng]
Persistent identifier
Erschienen in
Titel
Journal of Machine Learning Research
Band
24
Ausgabe
1
ISSN
1532-4435
Erscheinungsdatum
2023
Seitenanfang
1
Seitenende
37
Publication
Journal of Machine Learning Research
Erscheinungsdatum
2023
Zugänglichkeit
Rechte
Rechteangabe
© 2023 Radu Ioan Boţ, Michael Sedlmayer and Phan Tu Vuong
Universität Wien | Universitätsring 1 | 1010 Wien | T
+43-1-4277-0