You are here

Fisher consistency of supervised learning methods.

Event date: 
Thursday, 14 May, 2015 - 14:30
Seminar title: 
Fisher consistency of supervised learning methods.
Fabian Pedregosa
University of Paris-Dauphine

Many of the classification algorithms developed in the machine learning literature, including the support vector machine and boosting, can be viewed as methods that minimize a convex surrogate of the 0-1 loss. The convexity makes these algorithms computationally efficient. The use of a surrogate, however, has statistical consequences that must be balanced against the computational virtues of convexity. One property that establishes the optimality (under assumptions) for a classifier obtained by a minimization procedure such as support vector machine is that of Fisher consistency. In this talk I will describe first the notion of Fisher consistency on this setting and then describe the main results that have been emerged in recent years. In particular, I will review results for binary, multiclass classification and ranking algorithms. I will finish by stating novel results obtained for ordinal regression methods. 

Contact point: 

Emanuele Olivetti

Sala Kessler, FBK, Povo