Computer Science NASC Seminar

Accelerating First Order Methods For Convex Optimization Problems Arising In Machine Learning

Katya Scheinberg, Columbia University

May 07, 2010 10:00AM
Warren Weaver Hall, Room 1302
251 Mercer Street
New York, NY, 10012-1110
(Directions)

Spring 2010 NASC Seminars Calendar

Synopsis

First-order methods with favorable convergence rates have
recently become a focal point of much research in the field of convex
optimization. These methods have low per-iteration complexity and
hence are applicable to very large scale model, such as the ones
arising in signal processing, statistics and machine learning. We
will discuss several convex optimization problems arising in the
context of machine learning. We will show how various techniques can
be used to improve the performance of first order methods while
maintaining theoretical convergence rates.


top | contact webmaster