Smooth minimization of non-smooth functions
(2003)
Files
dp2003-12.pdf
Open Access - Adobe PDF
- 217.33 KB
Details
- Authors
- Abstract
- In this paper we propose a new approach for constructing efficient schemes for nonsmooth convex optimization. It is based on a special smoothing technique, which can be applied to the functions with explicit max-structure. Our approach can be considered as an alternative to black-box minimization. From the viewpoint of efficiency estimates, we manage to improve the traditional bounds on the number of iterations of the gradient schemes from 0 (1/e2) to 0 (1/e), keeping basically the complexity of each iteration unchanged.
- Affiliations
Citations
Nesterov, Y. (2003). Smooth minimization of non-smooth functions (CORE Discussion Papers 2003/12). https://hdl.handle.net/2078.5/32207