The Information Sieve

Author name not available (Why is that?)

Publication date: 8 July 2015

Abstract: We introduce a new framework for unsupervised learning of representations based on a novel hierarchical decomposition of information. Intuitively, data is passed through a series of progressively fine-grained sieves. Each layer of the sieve recovers a single latent factor that is maximally informative about multivariate dependence in the data. The data is transformed after each pass so that the remaining unexplained information trickles down to the next layer. Ultimately, we are left with a set of latent factors explaining all the dependence in the original data and remainder information consisting of independent noise. We present a practical implementation of this framework for discrete variables and apply it to a variety of fundamental tasks in unsupervised learning including independent component analysis, lossy and lossless compression, and predicting missing values in data.

Has companion code repository: https://github.com/gregversteeg/LinearSieve

This page was built for publication: The Information Sieve

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6263426)