EUVIMEDEUVIMED entdecken
Crossref

A Stochastic-Gradient-Based Interior-Point Algorithm for Solving Smooth Bound-Constrained Optimization Problems

Frank E. Curtis, Vyacheslav Kungurtsev, Daniel P. Robinson, Qi Wang

SIAM Journal on Optimization · 30.06.2025 · 35 (2) · 1030-1059

DOI: 10.1137/23m1569460 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SIAM Journal on Optimization, online erschienen am 14.05.2025. Verfasst von Frank E. Curtis und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 28 Literaturangaben. Gefördert von: OP VVV, Office of Naval Research, National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • OP VVV
  • Office of Naval Research
  • National Science Foundation

Zitieren

APA

Curtis, F. E., Kungurtsev, V., Robinson, D. P., & Wang, Q. (2025). A Stochastic-Gradient-Based Interior-Point Algorithm for Solving Smooth Bound-Constrained Optimization Problems. SIAM Journal on Optimization, 35(2), 1030-1059. https://doi.org/10.1137/23m1569460

Vancouver

Curtis FE, Kungurtsev V, Robinson DP, Wang Q. A Stochastic-Gradient-Based Interior-Point Algorithm for Solving Smooth Bound-Constrained Optimization Problems. SIAM Journal on Optimization. 2025;35(2):1030-1059. doi:10.1137/23m1569460

BibTeX
@article{Curtis2025,
  author = {Curtis, Frank E. and Kungurtsev, Vyacheslav and Robinson, Daniel P. and Wang, Qi},
  title = {A Stochastic-Gradient-Based Interior-Point Algorithm for Solving Smooth Bound-Constrained Optimization Problems},
  journal = {SIAM Journal on Optimization},
  year = {2025},
  volume = {35},
  number = {2},
  pages = {1030--1059},
  doi = {10.1137/23m1569460}
}
Kostenlos starten →