Who is Afraid of Non-Convex Loss Functions?

Posted in Science on August 06, 2008

Who is Afraid of Non-Convex Loss Functions?

The NIPS community has suffered of an acute convexivitis epidemic:

  •   ML applications seem to have trouble moving beyond logistic regression, SVMs, and exponential-family graphical models;
  •   For a new ML model, convexity is viewed as a virtue;
  •   Convexity is sometimes a virtue;
  •   But it is often a limitation.

ML theory has essentially never moved beyond convex models - the same way control theory has not really moved beyond linear systems.

Author: Yann Lecun, New York University

Watch Video

Tags: Science, Lectures, Computer Science, Machine Learning, VideoLectures.Net, Kernel Methods