Abstract
The minimum description length principle applied to function estimation can yield a criterion of the form - log(likelihood) + const · m instead of the familiar - log(likelihood) + (m/2) log n where m is the number of parameters and n is the sample size. The improved criterion yields minimax optimal rates for redundancy and statistical risk. The analysis suggests an information-theoretic reconciliation of criteria proposed by Rissanen, Schwarz, and Akaike.
Original language | English (US) |
---|---|
Title of host publication | IEEE International Symposium on Information Theory - Proceedings |
Publisher | IEEE |
State | Published - Dec 1 1994 |
Event | Proceedings of the 1994 IEEE International Symposium on Information Theory - Trodheim, Norw Duration: Jun 27 1994 → Jul 1 1994 |
Other
Other | Proceedings of the 1994 IEEE International Symposium on Information Theory |
---|---|
City | Trodheim, Norw |
Period | 6/27/94 → 7/1/94 |