# Numerical Analysis and Scientific Computing Seminar

## A generic acceleration scheme for large-scale gradient-based optimization

**Speaker:**
Zaid Harchaoui, CIMS

**Location:**
Warren Weaver Hall 1302

**Date:**
Feb. 26, 2016, 10 a.m.

**Synopsis:**

We introduce a generic scheme for accelerating first-order optimization methods in the sense of Nesterov, which builds upon a new analysis of the accelerated proximal point algorithm. Our approach consists of minimizing a convex objective by approximately solving a sequence of well-chosen auxiliary problems, leading to faster convergence. This strategy applies to a large class of algorithms, including gradient descent, block coordinate descent, SAG, SAGA, SDCA, SVRG, Finito/MISO, and their proximal variants. For all of these methods, we provide acceleration and explicit support for non-strongly convex objectives. In addition to theoretical speed-up, we also show that acceleration is useful in practice, especially for ill-conditioned problems where we measure significant improvements.

Joint work with Hongzhou Lin and Julien Mairal.

Related paper: http://arxiv.org/abs/1506.02186