Geodesic
Accelerated gradient sliding for minimizing a sum of functions
Doklady Rossijskoj akademii nauk. Matematika, informatika, processy upravleniâ, Tome 492 (2020), pp. 85-88

Voir la notice de l'article provenant de la source Math-Net.Ru

We propose a new way of justifying the accelerated gradient sliding of G. Lan, which allows one to extend the sliding technique to a combination of an accelerated gradient method with an accelerated variance reduction method. New optimal estimates for the solution of the problem of minimizing a sum of smooth strongly convex functions with a smooth regularizer are obtained.
Keywords: accelerated gradient sliding of G. Lan, accelerated variance reduction methods, smooth strongly convex functions. 
@article{DANMA_2020_492_a17,
     author = {D. M. Dvinskikh and S. S. Omelchenko and A. V. Gasnikov and A. I. Turin},
     title = {Accelerated gradient sliding for minimizing a sum of functions},
     journal = {Doklady Rossijskoj akademii nauk. Matematika, informatika, processy upravleni\^a},
     pages = {85--88},
     publisher = {mathdoc},
     volume = {492},
     year = {2020},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/DANMA_2020_492_a17/}
}
TY  - JOUR
AU  - D. M. Dvinskikh
AU  - S. S. Omelchenko
AU  - A. V. Gasnikov
AU  - A. I. Turin
TI  - Accelerated gradient sliding for minimizing a sum of functions
JO  - Doklady Rossijskoj akademii nauk. Matematika, informatika, processy upravleniâ
PY  - 2020
SP  - 85
EP  - 88
VL  - 492
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/DANMA_2020_492_a17/
LA  - ru
ID  - DANMA_2020_492_a17
ER  - 
%0 Journal Article
%A D. M. Dvinskikh
%A S. S. Omelchenko
%A A. V. Gasnikov
%A A. I. Turin
%T Accelerated gradient sliding for minimizing a sum of functions
%J Doklady Rossijskoj akademii nauk. Matematika, informatika, processy upravleniâ
%D 2020
%P 85-88
%V 492
%I mathdoc
%U http://geodesic.mathdoc.fr/item/DANMA_2020_492_a17/
%G ru
%F DANMA_2020_492_a17
D. M. Dvinskikh; S. S. Omelchenko; A. V. Gasnikov; A. I. Turin. Accelerated gradient sliding for minimizing a sum of functions. Doklady Rossijskoj akademii nauk. Matematika, informatika, processy upravleniâ, Tome 492 (2020), pp. 85-88. http://geodesic.mathdoc.fr/item/DANMA_2020_492_a17/