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: 4223
Tags: education engedu google googletechtalks talk talks techtalk techtalks
We
Strongly Recommends -
Aweber Autoresponders!
|
If you hobnob with any
other free autoresponder or paid services and later on if you want a
switch to Aweber, you
can't import your list to Aweber unless with double-op-in
again! So if you are new and starting fresh -- start with
Aweber. It is strongly suggested that you watch these
Video Tutorials on Aweber before you decide on
anything else. |
Video Comments
|
charfidil (November 30, 1999 at 12:00 am)
I don't understand. D':
pedrohsteixeira (November 30, 1999 at 12:00 am)
beamer class rules :)
bansaioslo (November 30, 1999 at 12:00 am)
nice, latex slides :)
badboy4life414 (November 30, 1999 at 12:00 am)
sweet little clever young maan.. How old are you and whar do you do for a living ?? regards.. |
