THEORY

RESEARCH

Learning Optimal Representations with the Decodable Information Bottleneck

November 30, 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.

Download the Paper

AUTHORS

Written by

Rama Vedantam

David Schwab

Douwe Kiela

Yann Dubois

Publisher

NeurIPS

Research Topics

Theory

Related Publications

July 08, 2024

THEORY

CORE MACHINE LEARNING

An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes

Antonio Orvieto, Lin Xiao

July 08, 2024

March 28, 2024

THEORY

CORE MACHINE LEARNING

On the Identifiability of Quantized Factors

Vitoria Barin Pacela, Kartik Ahuja, Simon Lacoste-Julien, Pascal Vincent

March 28, 2024

July 08, 2023

THEORY

NLP

Language acquisition: do children and language models follow similar learning stages?

Linnea Evanson, Yair Lakretz, Jean Remi King

July 08, 2023

May 01, 2023

THEORY

CORE MACHINE LEARNING

Meta-Learning in Games

Keegan Harris, Ioannis Anagnostides, Gabriele Farina, Mikhail Khodak, Zhiwei Steven Wu, Tuomas Sandholm, Maria-Florina Balcan

May 01, 2023

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.