Corpus ID: 14766269

THE MDL PRINCIPLE , PENALIZED LIKELIHOODS , AND STATISTICAL RISK

@inproceedings{Barron2008THEMP,
  title={THE MDL PRINCIPLE , PENALIZED LIKELIHOODS , AND STATISTICAL RISK},
  author={A. Barron and C. Huang and LI JONATHANQ. and X. Luo},
  year={2008}
}
We determine, for both countable and uncountable collections of functions, informationtheoretic conditions on a penalty pen(f) such that the optimizer f̂ of the penalized log likelihood criterion log 1/likelihood(f) + pen(f) has statistical risk not more than the index of resolvability corresponding to the accuracy of the optimizer of the expected value of the criterion. If F is the linear span of a dictionary of functions, traditional description-length penalties are based on the number of non… Expand
14 Citations
MDL, penalized likelihood, and statistical risk
  • 13
  • PDF
MDL Procedures with ` 1 Penalty and their Statistical Risk
  • 6
  • PDF
Information Theory of Penalized Likelihoods and its Statistical Implications
  • 5
  • Highly Influenced
  • PDF
A non-asymptotic penalization criterion for model selection in mixture of experts models
  • 1
  • PDF
Information theoretic validity of penalized likelihood
  • S. Chatterjee, A. Barron
  • Mathematics, Computer Science
  • 2014 IEEE International Symposium on Information Theory
  • 2014
  • 10
  • PDF
Finite-Sample Risk Bounds for Maximum Likelihood Estimation With Arbitrary Penalties
  • 1
  • PDF
Minimum Description Length Revisited
  • 10
  • PDF
Minimax lower bounds for ridge combinations including neural nets
  • 13
  • PDF
Noisy inductive matrix completion under sparse factor models
  • 6
  • PDF
...
1
2
...

References

SHOWING 1-10 OF 97 REFERENCES
An Asymptotic Property of Model Selection Criteria
  • 108
  • PDF
ON THE METHOD OF PENALIZATION
  • 31
  • PDF
Risk of penalized least squares, greedy selection andl 1-penalization for flexible function libraries
  • 44
  • Highly Influential
  • PDF
Probability inequalities for likelihood ratios and convergence rates of sieve MLEs
  • 265
Multiscale likelihood analysis and complexity penalized estimation
  • 128
  • PDF
Information-theoretic asymptotics of Bayes methods
  • 442
  • PDF
Asymptotic Analysis of Penalized Likelihood and Related Estimators
  • 218
  • PDF
Sparse Density Estimation with l1 Penalties
  • 61
  • PDF
Nonparametric roughness penalties for probability densities
  • 335
...
1
2
3
4
5
...