A probabilistic incremental proximal gradient method - Archive ouverte HAL Access content directly
Journal Articles IEEE Signal Processing Letters Year : 2019

A probabilistic incremental proximal gradient method

Abstract

In this paper, we propose a probabilistic optimization method, named probabilistic incremental proximal gradient (PIPG) method, by developing a probabilistic interpretation of the incremental proximal gradient algorithm. We explicitly model the update rules of the incremental proximal gradient method and develop a systematic approach to propagate the uncertainty of the solution estimate over iterations. The PIPG algorithm takes the form of Bayesian filtering updates for a state-space model constructed by using the cost function. Our framework makes it possible to utilize well-known exact or approximate Bayesian filters, such as Kalman or extended Kalman filters, to solve large scale regularized optimization problems.

Dates and versions

hal-01946642 , version 1 (06-12-2018)

Identifiers

Cite

Ömer Deniz Akyildiz, Emilie Chouzenoux, Víctor Elvira, Joaquín Míguez. A probabilistic incremental proximal gradient method. IEEE Signal Processing Letters, 2019, 26 (8), pp.1257-1261. ⟨10.1109/LSP.2019.2926926⟩. ⟨hal-01946642⟩
182 View
0 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More