Nalaganje...

An incremental mirror descent subgradient algorithm with random sweeping and proximal step

We investigate the convergence properties of incremental mirror descent type subgradient algorithms for minimizing the sum of convex functions. In each step, we only evaluate the subgradient of a single component function and mirror it back to the feasible domain, which makes iterations very cheap t...

Popoln opis

Shranjeno v:
Bibliografske podrobnosti
izdano v:Optimization
Main Authors: Boţ, Radu Ioan, Böhm, Axel
Format: Artigo
Jezik:Inglês
Izdano: Taylor & Francis 2018
Teme:
Online dostop:https://ncbi.nlm.nih.gov/pmc/articles/PMC6382287/
https://ncbi.nlm.nih.gov/pubmed/30828224
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1080/02331934.2018.1482491
Oznake: Označite
Brez oznak, prvi označite!