Who is Afraid of Non-Convex Loss Functions?
Dec 29, 2007 47363 views 
en-de
en-es
en-fr
en-pt
en
en-zh
en-sl
0.25
0.5
0.75
1.25
1.5
1.75
2
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.