Отправить статью по E-mail Universal Method for Stochastic Composite Optimization Problems
- Авторы: Gasnikov A.V.1,2, Nesterov Y.E.3,4
-
Учреждения:
- Institute for Information Transmission Problems
- Moscow Institute of Physics and Technology
- National Research University Higher School of Economics
- Aff4
- Выпуск: Том 58, № 1 (2018)
- Страницы: 48-64
- Раздел: Article
- URL: https://journals.rcsi.science/0965-5425/article/view/179966
- DOI: https://doi.org/10.1134/S0965542518010050
- ID: 179966
Цитировать
Открытый доступ
Доступ предоставлен
Только для подписчиков
Аннотация
A fast gradient method requiring only one projection is proposed for smooth convex optimization problems. The method has a visual geometric interpretation, so it is called the method of similar triangles (MST). Composite, adaptive, and universal versions of MST are suggested. Based on MST, a universal method is proposed for the first time for strongly convex problems (this method is continuous with respect to the strong convexity parameter of the smooth part of the functional). It is shown how the universal version of MST can be applied to stochastic optimization problems.
Об авторах
A. Gasnikov
Institute for Information Transmission Problems; Moscow Institute of Physics and Technology
Автор, ответственный за переписку.
Email: gasnikov.av@mipt.ru
Россия, Moscow, 127051; Dolgoprudnyi, Moscow oblast, 141700
Yu. Nesterov
National Research University Higher School of Economics; Aff4
Email: gasnikov.av@mipt.ru
Россия, Moscow, 101000; Voie du Roman Pays 34, Louvain-la-Neuve, L1.03.01–B-1348
Дополнительные файлы
