Learning Optimal Representations with the Decodable Information Bottleneck

arXiv2009.12789MaRDI QIDQ6349958

Author name not available (Why is that?)

Publication date: 27 September 2020

Abstract: We address the question of characterizing and finding optimal representations for supervised learning. Traditionally, this question has been tackled using the Information Bottleneck, which compresses the inputs while retaining information about the targets, in a decoder-agnostic fashion. In machine learning, however, our goal is not compression but rather generalization, which is intimately linked to the predictive family or decoder of interest (e.g. linear classifier). We propose the Decodable Information Bottleneck (DIB) that considers information retention and compression from the perspective of the desired predictive family. As a result, DIB gives rise to representations that are optimal in terms of expected test performance and can be estimated with guarantees. Empirically, we show that the framework can be used to enforce a small generalization gap on downstream classifiers and to predict the generalization ability of neural networks.

Has companion code repository: https://github.com/YannDubs/Mini_Decodable_Information_Bottleneck

This page was built for publication: Learning Optimal Representations with the Decodable Information Bottleneck

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6349958)