Regularized Quasi-monotone Method for Stochastic Optimization

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00367591" target="_blank" >RIV/68407700:21230/23:00367591 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1007/s11590-022-01931-4" target="_blank" >https://doi.org/10.1007/s11590-022-01931-4</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/s11590-022-01931-4" target="_blank" >10.1007/s11590-022-01931-4</a>

Result language
angličtina
Original language name
Regularized Quasi-monotone Method for Stochastic Optimization
Original language description
We adapt the quasi-monotone method, an algorithm characterized by uniquely having convergence quality guarantees for the last iterate, for composite convex minimization in the stochastic setting. For the proposed numerical scheme we derive the optimal convergence rate of O(1k+1) in terms of the last iterate, rather than on average as it is standard for subgradient methods. The theoretical guarantee for individual convergence of the regularized quasi-monotone method is confirmed by numerical experiments on ℓ1-regularized robust linear regression.
Czech name
—
Czech description
—

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)

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)

Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)