# The Information Sieve

arXiv: https://arxiv.org/abs/1507.02284 · HTML: https://mlsanity.com/paper/1507.02284/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2015.

## Built on by (most cited first, 1 of 1)

- [Video and Language Alignment in 2D Systems for 3D Multi-object Scenes with Multi-Information Derivative-Free Control](https://mlsanity.com/paper/2512.24826/) (2025)

## Abstract (arXiv)

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.