Sharpness, Restart and Acceleration.

  • TITLE: Sharpness, Restart and Acceleration.

  • AUTHORS: Vincent Roulet, Alexandre d'Aspremont.

  • ABSTRACT: The Lojasievicz inequality shows that sharpness bounds on the minimum of convex optimization problems hold almost generically. Here, we show that sharpness directly controls the performance of restart schemes. The constants quantifying sharpness are of course unobservable, but we show that optimal restart strategies are fairly robust, and searching for the best scheme only increases the complexity by a logarithmic factor compared to the optimal bound. Overall then, restart schemes generically accelerate accelerated methods.

  • STATUS: Preprint.

  • ArXiv PREPRINT: 1702.03828

  • PAPER: Sharpness, Restart and Acceleration in pdf