Text

The Generalized Bregman Distance

Recently, a new kind of distance has been introduced for the graphs of two point-to-set operators, one of which is maximally monotone. When both operators are the subdifferential of a proper lower semicontinuous convex function, this kind of distance specializes under modest assumptions to the classical Bregman distance. We name this new kind of distance the generalized Bregman distance, and we shed light on it with examples that utilize the other two most natural representative functions: the Fitzpatrick function and its conjugate. We provide sufficient conditions for convexity, coercivity, and supercoercivity: properties which are essential for implementation in proximal point type algorithms. We establish these results for both the left and right variants of this new kind of distance. We construct examples closely related to the Kullback--Leibler divergence, which was previously considered in the context of Bregman distances and whose importance in information theory is well known. In so doing, we demonstrate how to compute a difficult Fitzpatrick conjugate function, and we discover natural occurrences of the Lambert ${\mathcal W}$ function, whose importance in optimization is of growing interest.


Read More: https://epubs.siam.org/doi/abs/10.1137/19M1288140

Ketersediaan

Informasi Detail

Judul Seri

SIAM JOURNAL ON OPTIMIZATION; Vol.31 No.1 January-March 2021

No. Panggil

-

Penerbit

: .,

Deskripsi Fisik

p. 404 - 424

Bahasa

English

ISBN/ISSN

-

Klasifikasi

-

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

REGULARIZATION
CONVEX FUNCTION
FITZPATRICK FUNCTION
BREGMAN DISTANCE
GENERALIZED BREGMAN DISTANCE
FITZPATRICK DISTANCE
REPRESENTATIVE FUNCTION

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Regina S. Burachik, Minh N. Dao, Scott B. Lindstrom

Versi lain/terkait

Lampiran Berkas

Komentar