|
Optimization, Support Vector Machines, and Machine
Learning
Chih-Jen Lin
National Taiwan University
Hosted by Jorge More'
10:30 AM, June 23, 2006
Building 221, Room A216
|
| Abstract |
Optimization plays an important role in many machine learning methods.
However, traditionally the two areas have very different focuses. On the
one hand, machine learning work may not suitably use
optimization techniques. On the other hand, when optimization researchers
apply their methodology to machine learning, they may wrongly consider
irrelevant issues. In this talk I will discuss my experiences on support
vector machines (SVM), a useful machine learning method which involves
several challenging optimization problems. As a machine learning
researcher with an optimization background, I will show lessons learned in
the past and how we eventually construct the most widely used SVM
software.
|
