Solutions of learning problems by Empirical Risk Minimization (ERM) need to be consistent, so that they may be predictive. They also need to be well-posed, so that they can be used robustly. We show that a statistical form of well-posedness, defined in terms of the key property of L-stability, is necessary and sufficient for consistency of ERM. / revised July 2003
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/5507 |
| Date | 01 December 2002 |
| Creators | Mukherjee, Sayan, Niyogi, Partha, Poggio, Tomaso, Rifkin, Ryan |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 24 p., 1854466 bytes, 400508 bytes, application/postscript, application/pdf |
| Relation | AIM-2002-024, CBCL-223 |
Page generated in 0.0018 seconds