Contracting Proximal Methods for Smooth Convex Optimization
(2020) SIAM Journal on Optimization — Vol. 30, n° 4, p. 3146-3169 (2020)
Files
CORE_RP_3247.pdf
Open Access - Adobe PDF
- 1.14 MB
Details
- Authors
- Abstract
- In this paper, we propose new accelerated methods for smooth convex optimization, called contracting proximal methods. At every step of these methods, we need to minimize a contracted version of the objective function augmented by a regularization term in the form of Bregman divergence. We provide global convergence analysis for a general scheme admitting inexactness in solving the auxiliary subproblem. In the case of using for this purpose high-order tensor methods, we demonstrate an acceleration effect for both convex and uniformly convex composite objective functions. Thus, our construction explains acceleration for methods of any order starting from one. The augmentation of the number of calls of oracle due to computing the contracted proximal steps is limited by the logarithmic factor in the worst-case complexity bound.
- Affiliations
Citations
Doikov, N., & Nesterov, Y. (2020). Contracting Proximal Methods for Smooth Convex Optimization. SIAM Journal on Optimization, 30(4), 3146-3169. https://doi.org/10.1137/19M130769X (Original work published 2020)