Distributed Stochastic Nonsmooth Nonconvex Optimization

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F22%3A00360156" target="_blank" >RIV/68407700:21230/22:00360156 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1016/j.orl.2022.09.001" target="_blank" >https://doi.org/10.1016/j.orl.2022.09.001</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.orl.2022.09.001" target="_blank" >10.1016/j.orl.2022.09.001</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Distributed Stochastic Nonsmooth Nonconvex Optimization

Popis výsledku v původním jazyce

Distributed consensus optimization has received considerable attention in recent years and several distributed consensus-based algorithms have been proposed for (nonsmooth) convex and (smooth) nonconvex objective functions. However, the behavior of these distributed algorithms on nonconvex, nonsmooth and stochastic objective functions is not understood. Such class of functions and distributed setting are motivated by several applications, including problems in machine learning and signal processing. This paper presents the first convergence analysis of the decentralized stochastic subgradient method for such classes of problems, over networks modeled as undirected, fixed, graphs.

Název v anglickém jazyce

Distributed Stochastic Nonsmooth Nonconvex Optimization

Popis výsledku anglicky

Distributed consensus optimization has received considerable attention in recent years and several distributed consensus-based algorithms have been proposed for (nonsmooth) convex and (smooth) nonconvex objective functions. However, the behavior of these distributed algorithms on nonconvex, nonsmooth and stochastic objective functions is not understood. Such class of functions and distributed setting are motivated by several applications, including problems in machine learning and signal processing. This paper presents the first convergence analysis of the decentralized stochastic subgradient method for such classes of problems, over networks modeled as undirected, fixed, graphs.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Výzkumné centrum informatiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Operations Research Letters

ISSN

0167-6377

e-ISSN

1872-7468

Svazek periodika

50

Číslo periodika v rámci svazku

6

Stát vydavatele periodika

NL - Nizozemsko

Počet stran výsledku

5

Strana od-do

627-631

Kód UT WoS článku

000876521300001

EID výsledku v databázi Scopus

2-s2.0-85138836354