KFU. Card publication. Adaptive Conditional Gradient Method

KAZAN
FEDERAL UNIVERSITY

- RUS
- 中文
- ES

ADAPTIVE CONDITIONAL GRADIENT METHOD

Form of presentation

Articles in international journals and collections

Year of publication

2019

Язык

английский

Authors, employees of KFU

Gabidullina Zulfiya Ravilevna, author

Bibliographic description in the original language

Gabidullina Z.R., Adaptive Conditional Gradient Method//Journal of Optimization Theory and Applications. - 2019. - Vol.183, Is.3. - P.1077-1098.

Annotation

We present a novel fully adaptive conditional gradient method with the step length regulation for solving pseudo-convex constrained optimization problems. We propose some deterministic rules of the step length regulation in a normalized direction. These rules guarantee to find the step length by utilizing the finite procedures and provide the strict relaxation of the objective function at each iteration. We prove that the sequence of the function values for the iterates generated by the algorithm converges globally to the objective function optimal value with sublinear rate.

Keywords

Optimization problems, Pseudo-convex function, Adaptation, Descent direction, Normalization, Step length Regulation, Rate of convergence.

The name of the journal

Journal of Optimization Theory and Applications

URL

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85074016312&doi=10.1007%2fs10957-019-01585-w&partnerID=40&md5=61f69fdf521f5d9717001747d2b37c40

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

https://repository.kpfu.ru/eng/?p_id=215227&p_lang=2

Full metadata record

Field DC	Value	Language
dc.contributor.author	Gabidullina Zulfiya Ravilevna	ru_RU
dc.date.accessioned	2019-01-01T00:00:00Z	ru_RU
dc.date.available	2019-01-01T00:00:00Z	ru_RU
dc.date.issued	2019	ru_RU
dc.identifier.citation	Gabidullina Z.R., Adaptive Conditional Gradient Method//Journal of Optimization Theory and Applications. - 2019. - Vol.183, Is.3. - P.1077-1098.	ru_RU
dc.identifier.uri	https://repository.kpfu.ru/eng/?p_id=215227&p_lang=2	ru_RU
dc.description.abstract	Journal of Optimization Theory and Applications	ru_RU
dc.description.abstract	We present a novel fully adaptive conditional gradient method with the step length regulation for solving pseudo-convex constrained optimization problems. We propose some deterministic rules of the step length regulation in a normalized direction. These rules guarantee to find the step length by utilizing the finite procedures and provide the strict relaxation of the objective function at each iteration. We prove that the sequence of the function values for the iterates generated by the algorithm converges globally to the objective function optimal value with sublinear rate.	ru_RU
dc.language.iso	ru	ru_RU
dc.subject	Optimization problems	ru_RU
dc.subject	Pseudo-convex function	ru_RU
dc.subject	Adaptation	ru_RU
dc.subject	Descent direction	ru_RU
dc.subject	Normalization	ru_RU
dc.subject	Step length Regulation	ru_RU
dc.subject	Rate of convergence.	ru_RU
dc.title	Adaptive Conditional Gradient Method	ru_RU
dc.type	Articles in international journals and collections	ru_RU