A Stochastic-Gradient-Based Interior-Point Algorithm for Solving Smooth Bound-Constrained Optimization Problems
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00383481" target="_blank" >RIV/68407700:21230/25:00383481 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1137/23M1569460" target="_blank" >https://doi.org/10.1137/23M1569460</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1137/23M1569460" target="_blank" >10.1137/23M1569460</a>
Alternative languages
Result language
angličtina
Original language name
A Stochastic-Gradient-Based Interior-Point Algorithm for Solving Smooth Bound-Constrained Optimization Problems
Original language description
A stochastic-gradient-based interior-point algorithm for minimizing a continuously differentiable objective function (that may be nonconvex) subject to bound constraints is presented, analyzed, and demonstrated through experimental results. The algorithm is unique from other interior-point methods for solving smooth nonconvex optimization problems since the search directions are computed using stochastic gradient estimates. It is also unique in its use of inner neighborhoods of the feasible region—defined by a positive and vanishing neighborhood-parameter sequence—in which the iterates are forced to remain. It is shown that with a careful balance between the barrier, step size, and neighborhood sequences, the proposed algorithm satisfies convergence guarantees in both deterministic and stochastic settings. The results of numerical experiments show that in both settings the algorithm can outperform projection-based methods.
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
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
SIAM Journal on Optimization
ISSN
1052-6234
e-ISSN
1095-7189
Volume of the periodical
35
Issue of the periodical within the volume
2
Country of publishing house
US - UNITED STATES
Number of pages
30
Pages from-to
1030-1059
UT code for WoS article
001504739900013
EID of the result in the Scopus database
2-s2.0-105005263643