A Zeroth Order Method for Stochastic Weakly Convex Optimization
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00352286" target="_blank" >RIV/68407700:21230/21:00352286 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1007/s10589-021-00313-3" target="_blank" >https://doi.org/10.1007/s10589-021-00313-3</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/s10589-021-00313-3" target="_blank" >10.1007/s10589-021-00313-3</a>
Alternative languages
Result language
angličtina
Original language name
A Zeroth Order Method for Stochastic Weakly Convex Optimization
Original language description
In this paper, we consider stochastic weakly convex optimization problems, however without the existence of a stochastic subgradient oracle. We present a derivative free algorithm that uses a two point approximation for computing a gradient estimate of the smoothed function. We prove convergence at a similar rate as state of the art methods, however with a larger constant, and report some numerical results showing the effectiveness of the approach.
Czech name
—
Czech description
—
Classification
Type
J<sub>imp</sub> - Article in a specialist periodical, which is included in the Web of Science database
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Research Center for Informatics</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
Computational Optimization and Applications
ISSN
0926-6003
e-ISSN
1573-2894
Volume of the periodical
80
Issue of the periodical within the volume
September
Country of publishing house
CH - SWITZERLAND
Number of pages
23
Pages from-to
731-753
UT code for WoS article
000691934800001
EID of the result in the Scopus database
2-s2.0-85114032255