Unifying mirror descent and dual averaging

Authors:
  • AJAnatoli Juditsky
    Anatoli Juditsky
  • JKJoon Kwon
    Joon Kwon
  • ÉMÉric Moulines
    Éric Moulines

Abstract
We introduce and analyze a new family of first-order optimization algorithms which generalizes and unifies both mirror descent and dual averaging. Within the framework of this family, we define new algorithms for constrained optimization that combines the advantages of mirror descent and dual averaging. Our preliminary simulation study shows that these new algorithms significantly outperform available methods in some situations.

This publication has 14 references indexed in Scilit: