Sampling from Non-smooth Distributions Through Langevin Diffusion

In this paper, we propose proximal splitting-type algorithms for sampling from distributions whose densities are not necessarily smooth nor log-concave. Our approach brings together tools from, on the one hand, variational analysis and non-smooth optimization, and on the other hand, stochastic diffu...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Methodology and computing in applied probability Jg. 23; H. 4; S. 1173 - 1201
Hauptverfasser:	Luu, Tung Duy, Fadili, Jalal, Chesneau, Christophe
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York Springer US 01.12.2021 Springer Nature B.V Springer Verlag
Schlagworte:	Algorithms Business and Management Computer Science Diffusion Economics Electrical Engineering Fines & penalties Life Sciences Machine Learning Mathematics Mathematics and Statistics Numerical Analysis Optimization Optimization and Control Sampling Signal and Image Processing Statistics Statistics Theory 65C30 Langevin diffusion Exponentially weighted aggregation Proximal splitting Monte-Carlo 65C05 Non-smooth distributions 65C60 65C50
ISSN:	1387-5841, 1573-7713
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!