# A Theory of Feature Learning

arXiv: https://arxiv.org/abs/1504.00083 · HTML: https://mlsanity.com/paper/1504.00083/

## Key facts

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

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

- [Comparing Corrupted Constrained Learning Problems](https://mlsanity.com/paper/2608.25745/) (2026)

## Abstract (arXiv)

Feature Learning aims to extract relevant information contained in data sets in an automated fashion. It is driving force behind the current deep learning trend, a set of methods that have had widespread empirical success. What is lacking is a theoretical understanding of different feature learning schemes. This work provides a theoretical framework for feature learning and then characterizes when features can be learnt in an unsupervised fashion. We also provide means to judge the quality of features via rate-distortion theory and its generalizations.