Delayed feedback in online non-convex optimization: A non-stationary approach with applications
Numerical Algorithms · 2026-11 · 103 (3) · 1597-1638
DOI: 10.1007/s11075-025-02276-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Numerical Algorithms, online erschienen am 29.11.2025. Verfasst von Felipe Lara und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Agencia Nacional de Investigación y Desarrollo, UTA research project Fortalecimientos Grupos de Investigación Código.
Abstract (Originalsprache)
We study non-convex online optimization problems with delay and noise by evaluating dynamic regret in the non-stationary setting when the loss functions are quasar-convex. In particular, we consider scenarios involving quasar-convex functions either with Lipschitz gradients or with weak smoothness, and in each case we establish bounded dynamic regret in terms of cumulative path variation, achieving sub-linear rates. Furthermore, we illustrate the flexibility of our framework by applying it to both thThe average execution time for each experiment is alsoincluded.eoretical settings, such as zeroth-order (bandit), and practical applications with quadratic fractional functions. Moreover, we provide new examples of non-convex functions that are quasar-convex by proving that the class of differentiable strongly quasiconvex functions is strongly quasar-convex on convex compact sets. Finally, several numerical experiments validate our theoretical findings, illustrating the effectiveness of our approach.
Förderung
- Agencia Nacional de Investigación y Desarrollo
- UTA research project Fortalecimientos Grupos de Investigación Código
Zitieren
APA
Lara, F., & Vega, C. (2026). Delayed feedback in online non-convex optimization: A non-stationary approach with applications. Numerical Algorithms, 103(3), 1597-1638. https://doi.org/10.1007/s11075-025-02276-6
Vancouver
Lara F, Vega C. Delayed feedback in online non-convex optimization: A non-stationary approach with applications. Numerical Algorithms. 2026;103(3):1597-1638. doi:10.1007/s11075-025-02276-6
BibTeX
@article{Lara2026,
author = {Lara, Felipe and Vega, Cristian},
title = {Delayed feedback in online non-convex optimization: A non-stationary approach with applications},
journal = {Numerical Algorithms},
year = {2026},
volume = {103},
number = {3},
pages = {1597--1638},
doi = {10.1007/s11075-025-02276-6}
}
EUVIMED