A Bregman inertial forward-reflected-backward method for nonconvex minimization

We propose a Bregman inertial forward-reflected-backward (BiFRB) method for nonconvex composite problems. Assuming the generalized concave Kurdyka-Łojasiewicz property, we obtain sequential convergence of BiFRB, as well as convergence rates on both the function value and actual sequence. One disting...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Journal of global optimization Ročník 89; číslo 2; s. 327 - 354
Hlavní autori:	Wang, Xianfu, Wang, Ziyuan
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York Springer US 01.06.2024 Springer Springer Nature B.V
Predmet:	Algorithms Analysis Computer Science Convergence Euclidean space Mathematics Mathematics and Statistics Methods Numerical analysis Operations Research/Decision Theory Optimization Parameters Real Functions Nonconvex optimization 49J52 Secondary 26D10 Generalized concave Kurdyka-Łojasiewicz property Forward-reflected-backward splitting Bregman proximal mapping Inertial effect Primary 90C26 Implicit merit function
ISSN:	0925-5001, 1573-2916
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Buďte prvý, kto okomentuje tento záznam!