EUVIMEDEUVIMED entdecken
Crossref

Methods for Optimization Problems with Markovian Stochasticity and Non-Euclidean Geometry

Vladimir Solodkin, Andrey Veprikov, Alexander Chernyavskiy, Aleksandr Beznosikov

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (30) · 25508-25517

DOI: 10.1609/aaai.v40i30.39746 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Vladimir Solodkin und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper examines a variety of classical optimization problems, including well-known minimization tasks and more general variational inequalities. We consider a stochastic formulation of these problems and, unlike most previous work, we take into account the complex Markov nature of the noise. We also consider the geometry of the problem in an arbitrary non-Euclidean setting and propose four methods based on the Mirror Descent iteration technique. The theoretical analysis is provided for smooth and convex minimization problems and variational inequalities with Lipschitz and monotone operators. The convergence guarantees obtained are optimal for first-order stochastic methods, as evidenced by the lower bound estimates provided in this paper. In order to validate the theoretical results, we present the relevant numerical experiments on various reinforcement learning tasks.

Zitieren

APA

Solodkin, V., Veprikov, A., Chernyavskiy, A., & Beznosikov, A. (2026). Methods for Optimization Problems with Markovian Stochasticity and Non-Euclidean Geometry. Proceedings of the AAAI Conference on Artificial Intelligence, 40(30), 25508-25517. https://doi.org/10.1609/aaai.v40i30.39746

Vancouver

Solodkin V, Veprikov A, Chernyavskiy A, Beznosikov A. Methods for Optimization Problems with Markovian Stochasticity and Non-Euclidean Geometry. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(30):25508-25517. doi:10.1609/aaai.v40i30.39746

BibTeX
@article{Solodkin2026,
  author = {Solodkin, Vladimir and Veprikov, Andrey and Chernyavskiy, Alexander and Beznosikov, Aleksandr},
  title = {Methods for Optimization Problems with Markovian Stochasticity and Non-Euclidean Geometry},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {30},
  pages = {25508--25517},
  doi = {10.1609/aaai.v40i30.39746}
}
Kostenlos starten →