The Information Bottleneck Problem and its Applications in Machine Learning

Inference capabilities of machine learning (ML) systems skyrocketed in recent years, now playing a pivotal role in various aspect of society. The goal in statistical learning is to use data to obtain simple algorithms for predicting a random variable Y from a correlated observation X . Since the...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal on selected areas in information theory 2020-05, Vol.1 (1), p.19-38
Main Authors: Goldfeld, Ziv, Polyanskiy, Yury
Format: Article
Language:English
Subjects:
Algorithms
Deep learning
Figure of merit
information bottleneck
Information theory
IP networks
Machine learning
Mutual information
neural networks
Noise measurement
Predictions
Random variables
Representations
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Inference capabilities of machine learning (ML) systems skyrocketed in recent years, now playing a pivotal role in various aspect of society. The goal in statistical learning is to use data to obtain simple algorithms for predicting a random variable Y from a correlated observation X . Since the dimension of X is typically huge, computationally feasible solutions should summarize it into a lower-dimensional feature vector T , from which Y is predicted. The algorithm will successfully make the prediction if T is a good proxy of Y , despite the said dimensionality-reduction. A myriad of ML algorithms (mostly employing deep learning (DL)) for finding such representations T based on real-world data are now available. While these methods are effective in practice, their success is hindered by the lack of a comprehensive theory to explain it. The information bottleneck (IB) theory recently emerged as a bold information-theoretic paradigm for analyzing DL systems. Adopting mutual information as the figure of merit, it suggests that the best representation T should be maximally informative about Y while minimizing the mutual information with X . In this tutorial we survey the information-theoretic origins of this abstract principle, and its recent impact on DL. For the latter, we cover implications of the IB problem on DL theory, as well as practical algorithms inspired by it. Our goal is to provide a unified and cohesive description. A clear view of current knowledge is important for further leveraging IB and other information-theoretic ideas to study DL models.
ISSN:2641-8770
2641-8770
DOI:10.1109/JSAIT.2020.2991561