Squared-loss Mutual Information Regularization: A Novel Information-theoretic Approach to Semi-supervised Learning

Gang Niu, Wittawat Jitkrittum, Bo Dai, Hirotaka Hachiya, Masashi Sugiyama
2013 International Conference on Machine Learning  
We propose squared-loss mutual information regularization (SMIR) for multi-class probabilistic classification, following the information maximization principle. SMIR is convex under mild conditions and thus improves the nonconvexity of mutual information regularization. It offers all of the following four abilities to semi-supervised algorithms: Analytical solution, out-of-sample/multi-class classification, and probabilistic output. Furthermore, novel generalization error bounds are derived.
more » ... eriments show SMIR compares favorably with state-of-the-art methods.
dblp:conf/icml/NiuJDHS13 fatcat:q27inx2isjbzngejj53frbjt4e