Material Detail

Who is Afraid of Non-Convex Loss Functions?

Who is Afraid of Non-Convex Loss Functions?

This video was recorded at NIPS Workshop on Efficient Machine Learning, Whistler 2007. 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.


  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material


Log in to participate in the discussions or sign up if you are not already a MERLOT member.