Optimization for Machine Learning

Back


Google Tech Talks March, 25 2008 ABSTRACT S.V.N. Vishwanathan - Research Scientist Regularized 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-smooth functions. 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 - Zurich S.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.

Category: People
Uploaded: March 26th, 2008 @ 2:12 am
Author: googletechtalks

Length: 55:44
Rating: Whole StarWhole StarWhole StarWhole StarHalf Star
Views: 2,248

Tags: education engedu google googletechtalks talk talks techtalk techtalks

Related Video Links:


» View Video Comments For Optimization for Machine Learning
» View googletechtalks's Other Uploaded Videos

Video Thumbnails:


Thumbnail #1 Video Thumbnail #1:
Thumbnail #2 Video Thumbnail #2:
Thumbnail #3 Video Thumbnail #3:


Video Embedding Code:


Video Url:


Embed Code:

* Embed this video on your website, social bookmark, myspace, or blog.