Information Bottleneck Analysis by a Conditional Mutual Information Bound |
| |
Authors: | Taro Tezuka Shizuma Namekawa |
| |
Affiliation: | 1.Faculty of Library, Information and Media Science, University of Tsukuba, Tsukuba, Ibaraki 305-8577, Japan;2.Graduate School of Library, Information and Media Studies, University of Tsukuba, Tsukuba, Ibaraki 305-8577, Japan; |
| |
Abstract: | Task-nuisance decomposition describes why the information bottleneck loss is a suitable objective for supervised learning. The true category y is predicted for input x using latent variables z. When n is a nuisance independent from y, can be decreased by reducing since the latter upper bounds the former. We extend this framework by demonstrating that conditional mutual information provides an alternative upper bound for . This bound is applicable even if z is not a sufficient representation of x, that is, . We used mutual information neural estimation (MINE) to estimate . Experiments demonstrated that is smaller than for layers closer to the input, matching the claim that the former is a tighter bound than the latter. Because of this difference, the information plane differs when is used instead of . |
| |
Keywords: | conditional mutual information information bottleneck deep learning |
|
|