Abstract
We derive upper bounds on the generalization error of a learning algorithm in terms of the mutual information between its input and output. The bounds provide an information-theoretic understanding of generalization in learning problems, and give theoretical guidelines for striking the right balance between data fit and generalization by controlling the input-output mutual information. We propose a number of methods for this purpose, among which are algorithms that regularize the ERM algorithm with relative entropy or with random noise. Our work extends and leads to nontrivial improvements on the recent results of Russo and Zou.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 2525-2534 |
| Number of pages | 10 |
| Journal | Advances in Neural Information Processing Systems |
| Volume | 2017-December |
| State | Published - 2017 |
| Event | 31st Annual Conference on Neural Information Processing Systems, NIPS 2017 - Long Beach, United States Duration: Dec 4 2017 → Dec 9 2017 |
ASJC Scopus subject areas
- Computer Networks and Communications
- Information Systems
- Signal Processing
Fingerprint Dive into the research topics of 'Information-theoretic analysis of generalization capability of learning algorithms'. Together they form a unique fingerprint.
Cite this
Xu, A., & Raginsky, M. (2017). Information-theoretic analysis of generalization capability of learning algorithms. Advances in Neural Information Processing Systems, 2017-December, 2525-2534.