Optimization for Machine Learning

Google Tech TalksMarch, 25 2008ABSTRACTS.V.N. Vishwanathan - Research ScientistRegularized risk minimization is at the heart of many machine learning algorithms. The underlying objective function to be minimized is convex, and often non-smooth. Classical optimization algorithms cannot handle this efficiently. In this talk we present two algorithms for dealing with convex non-smooth objective functions. First, we extend the well known BFGS quasi-Newton algorithm to handle non-smoothfunctions. Second, we show how bundle methods can be applied in a machine learning context. We present both theoretical and experimental justification of our algorithms.Speaker: S.V.N. Vishwanathan - Research Scientist - ZurichS.V.N Vishwanathan is a principal researcher in the Statistical Machine Learning program, National ICT Australia with an adjunct appointment at the College of Engineering and Computer Science(CECS), Australian National University. I got my Ph.D in 2002 from the Department of Computer Science and Automation (CSA) at the Indian Institute of Science.

Channel: People & Blogs
Uploaded: November 30, 1999 at 12:00 am
Author: googletechtalks

Length: 55:44
Rating: 4.67
Views: 4106

Tags: education  engedu  google  googletechtalks  talk  talks  techtalk  techtalks  

Video Comments