November 30, 2020
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.
Publisher
NeurIPS
Research Topics
March 28, 2024
Vitoria Barin Pacela, Kartik Ahuja, Simon Lacoste-Julien, Pascal Vincent
March 28, 2024
July 08, 2023
Linnea Evanson, Yair Lakretz, Jean Remi King
July 08, 2023
May 01, 2023
Keegan Harris, Ioannis Anagnostides, Gabriele Farina, Mikhail Khodak, Zhiwei Steven Wu, Tuomas Sandholm, Maria-Florina Balcan
May 01, 2023
November 30, 2022
Alexandre Defossez, Leon Bottou, Nicolas Usunier, Francis Bach
November 30, 2022
Product experiences
Foundational models
Product experiences
Latest news
Foundational models