On Stability and Concentration of Measure
Abstract
Stability conditions can be thought of as a way of controlling the variance of the learning process. Strong stability conditions additionally imply concentration of certain quantities around their expected values. It was shown recently that stability of learning algorithms is closely related to their generalization and consistency. In this paper we examine stability conditions from this point of view.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 01, 2004
- Accession Number
- ADA459829
Entities
People
- Alexander Rakhlin
- Sayan Mukherjee
- Tomaso Poggio
Organizations
- Massachusetts Institute of Technology