Computer Science – Learning
Scientific paper
2006-12-19
Computer Science
Learning
14 pages, LaTeX, no figures, IEEE Trans Inform. Th., to appear
Scientific paper
Approximation of the optimal two-part MDL code for given data, through successive monotonically length-decreasing two-part MDL codes, has the following properties: (i) computation of each step may take arbitrarily long; (ii) we may not know when we reach the optimum, or whether we will reach the optimum at all; (iii) the sequence of models generated may not monotonically improve the goodness of fit; but (iv) the model associated with the optimum has (almost) the best goodness of fit. To express the practically interesting goodness of fit of individual models for individual data sets we have to rely on Kolmogorov complexity.
Adriaans Pieter
Vitanyi Paul
No associations
LandOfFree
Approximation of the Two-Part MDL Code does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Approximation of the Two-Part MDL Code, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Approximation of the Two-Part MDL Code will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-315116