Forward-Backward Splitting with Bregman Distances

By Quang Van Nguyen. 2015

71 citations recorded by the source corpus.

We propose a forward-backward splitting algorithm based on Bregman distances for composite minimization problems in general reflexive Banach spaces. The convergence is established using the notion of variable quasi-Bregman monotone sequences. Various examples are discussed, including some in Euclidean spaces, where new algorithms are obtained.

Subfields: Computational Theory and Mathematics, Numerical Analysis

View Paper: https://www.semanticscholar.org/paper/1feac8826f2aae97abcc7c4c02d77b34ee0e3b6b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. G. Peyr'e
2. Bernhard Schmitzer
3. Franccois-Xavier Vialard
4. Lénaïc Chizat

In Numerical Analysis

1. G. Peyr'e
2. Bernhard Schmitzer
3. Franccois-Xavier Vialard
4. Lénaïc Chizat

Citations in the corpus

• Scaling Algorithms for Unbalanced Transport Problems (2016, methodology): “The most simple one is the proximal point algorithm [31], but most proximal splitting schemes have been extended to this setting, such as for instance ADMM [78], primal-dual schemes [23] and forward-backward [54].”