Convergence of the Iterates in Mirror Descent Methods

Thinh T. Doan, Subhonmesh Bose, D. Hoa Nguyen, Carolyn L. Beck

研究成果: Contribution to journalArticle

7 引用 (Scopus)

抜粋

We consider centralized and distributed mirror descent (MD) algorithms over a finite-dimensional Hilbert space, and prove that the problem variables converge to an optimizer of a possibly nonsmooth function when the step sizes are square summable but not summable. Prior literature has focused on the convergence of the function value to its optimum. However, applications from distributed optimization and learning in games require the convergence of the variables to an optimizer, which is generally not guaranteed without assuming strong convexity of the objective function. We provide numerical simulations comparing entropic MD and standard subgradient methods for the robust regression problem.

元の言語英語
ページ(範囲)114-119
ページ数6
ジャーナルIEEE Control Systems Letters
3
発行部数1
DOI
出版物ステータス出版済み - 1 2019

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Control and Optimization

フィンガープリント Convergence of the Iterates in Mirror Descent Methods' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用