Optimization for Machine Learning

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 & Blogs

Tags:

• google
• techtalks
• techtalk
• engedu
• talk
• talks
• googletechtalks
• education

[adelle0001]

ano daw! hindi ko masyadong magets! o.O

[YAKYAKYAK90]

Thanks a lot!

[plmqas]

buncha cruncha human

[charfidil]

I don't understand. D':

[pedrohsteixeira]

beamer class rules :)

[bansaioslo]

nice, latex slides :)

[badboy4life414]

sweet little clever young maan..

How old are you and whar do you do for a living ??

regards..