Minimum complexity density estimation
Andrew R. Barron, Thomas M. Cover · IEEE Transactions on Information Theory · 1991
The authors introduce an index of resolvability that is proved to bound the rate of convergence of minimum complexity density estimators as well as the information-theoretic redundancy of the corresponding total description length. The results on the index of resolvability demonstrate the statistical effectiveness of the minimum description-length principle as a method of inference. The minimum complexity estimator converges to true density nearly as fast as an estimator based on prior knowledge of the true subclass of densities. Interpretations and basic properties of minimum complexity estimators are discussed. Some regression and classification problems that can be examined from the minimum description-length framework are considered.>
Cited by 491 works. doi:10.1109/18.86996
Authors
References
- Information Theory and Reliable Communication
- Information Theory and Reliable Communication.
- Estimating the Dimension of a Model
- The Theory of Probability
- Information Theory and an Extension of the Maximum Likelihood Principle
- A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations
- Probability Inequalities for sums of Bounded Random Variables
- Modeling by shortest data description
- Probability Inequalities for Sums of Bounded Random Variables
- Sphere Packings, Lattices and Groups.