KFU. Card publication. A Fully Adaptive Steepest Descent Method

KAZAN
FEDERAL UNIVERSITY

- RUS
- 中文
- ES

A FULLY ADAPTIVE STEEPEST DESCENT METHOD

Form of presentation

Articles in international journals and collections

Year of publication

2021

Язык

английский

Authors, employees of KFU

Gabidullina Zulfiya Ravilevna, author

Bibliographic description in the original language

Z.R. Gabidullina A Fully Adaptive Steepest Descent Method, arXiv:2108.05027 (Mathematics: Optimization and Control) https://arxiv.org/abs/2108.05027 (WOS, Scopus preprint)

Annotation

arxiv.org

Keywords

pseudoconvex function, steepest descent, normaliza- tion of descent direction, adaptive step-size, rate of convergence

The name of the journal

arxiv.org

URL

https://arxiv.org/pdf/2108.05027.pdf

Please use this ID to quote from or refer to the card

https://repository.kpfu.ru/eng/?p_id=279775&p_lang=2

Full metadata record

Field DC	Value	Language
dc.contributor.author	Gabidullina Zulfiya Ravilevna	ru_RU
dc.date.accessioned	2021-01-01T00:00:00Z	ru_RU
dc.date.available	2021-01-01T00:00:00Z	ru_RU
dc.date.issued	2021	ru_RU
dc.identifier.citation	Z.R. Gabidullina A Fully Adaptive Steepest Descent Method, arXiv:2108.05027 (Mathematics: Optimization and Control) https://arxiv.org/abs/2108.05027 (WOS, Scopus preprint)	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/eng/?p_id=279775&p_lang=2	ru_RU
dc.description.abstract	arxiv.org	ru_RU
dc.description.abstract	For solving pseudo-convex global optimization problems, we present a novel fully adaptive steepest descent method (or ASDM) without any hard-to-estimate parameters. For the step-size regulation in an ε-normalized direction, we use the deterministic rules, which were proposed in J. Optim. Theory Appl. (2019,\, DOI: https://doi.org/10.1007/S10957-019-01585-W). We obtained the optimistic convergence estimates for the generated by ASDM sequence of iteration points. Namely, the sequence of function values of iterates has the advantage of the strict monotonic behaviour and globally converges to the objective function optimum with the sublinear rate. This rate of convergence is now known to be the best for the steepest descent method in the non-convex objectives context. Preliminary computational tests confirm the efficiency of the proposed method and low computational costs for its realization.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	pseudoconvex function	ru_RU
dc.subject	steepest descent	ru_RU
dc.subject	normaliza- tion of descent direction	ru_RU
dc.subject	adaptive step-size	ru_RU
dc.subject	rate of convergence	ru_RU
dc.title	A Fully Adaptive Steepest Descent Method	ru_RU
dc.type	Articles in international journals and collections	ru_RU