Effects of compression on language evolution
Artificial Life
Convergence and Error Bounds for Universal Prediction of Nonbinary Sequences
EMCL '01 Proceedings of the 12th European Conference on Machine Learning
Towards an Algorithmic Statistics
ALT '00 Proceedings of the 11th International Conference on Algorithmic Learning Theory
ISAAC '02 Proceedings of the 13th International Symposium on Algorithms and Computation
On different facets of regularization theory
Neural Computation
Journal of Logic, Language and Information
Optimality of universal Bayesian sequence prediction for general loss and alphabet
The Journal of Machine Learning Research
Predictability, Complexity, and Learning
Neural Computation
MDL convergence speed for Bernoulli sequences
Statistics and Computing
Interestingness measures for data mining: A survey
ACM Computing Surveys (CSUR)
Compact representations as a search strategy: compression EDAs
Theoretical Computer Science - Foundations of genetic algorithms
On generalized computable universal priors and their convergence
Theoretical Computer Science - Algorithmic learning theory
Denoising using local projective subspace methods
Neurocomputing
On semimeasures predicting Martin-Löf random sequences
Theoretical Computer Science
Ockham's razor, empirical complexity, and truth-finding efficiency
Theoretical Computer Science
A NON-PARAMETRIC APPROACH TO SIMPLICITY CLUSTERING
Applied Artificial Intelligence
Prefetching based on web usage mining
Proceedings of the ACM/IFIP/USENIX 2003 International Conference on Middleware
Hierarchical Extraction of Independent Subspaces of Unknown Dimensions
ICA '09 Proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation
Occam's Razor and a non-syntactic measure of decision tree complexity
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Using Kolmogorov complexity for understanding some limitations on steganography
ISIT'09 Proceedings of the 2009 IEEE international conference on Symposium on Information Theory - Volume 4
Sequential predictions based on algorithmic complexity
Journal of Computer and System Sciences
Computable Bayesian compression for uniformly discretizable statistical models
ALT'09 Proceedings of the 20th international conference on Algorithmic learning theory
Compression and learning in linear regression
ISMIS'11 Proceedings of the 19th international conference on Foundations of intelligent systems
Optimal bayesian 2d-discretization for variable ranking in regression
DS'06 Proceedings of the 9th international conference on Discovery Science
Compact genetic codes as a search strategy of evolutionary processes
FOGA'05 Proceedings of the 8th international conference on Foundations of Genetic Algorithms
| Hi-index | 754.84 |
The relationship between the Bayesian approach and the minimum description length approach is established. We sharpen and clarify the general modeling principles minimum description length (MDL) and minimum message length (MML), abstracted as the ideal MDL principle and defined from Bayes's rule by means of Kolmogorov complexity. The basic condition under which the ideal principle should be applied is encapsulated as the fundamental inequality, which in broad terms states that the principle is valid when the data are random, relative to every contemplated hypothesis and also these hypotheses are random relative to the (universal) prior. The ideal principle states that the prior probability associated with the hypothesis should be given by the algorithmic universal probability, and the sum of the log universal probability of the model plus the log of the probability of the data given the model should be minimized. If we restrict the model class to finite sets then application of the ideal principle turns into Kolmogorov's minimal sufficient statistic. In general, we show that data compression is almost always the best strategy, both in model selection and prediction