Falsification and future performance

Balduzzi, D

doi:10.1007/978-3-642-44958-1_5

Item

ITEM ACTIONSEXPORT

Add to Basket

Local TagsRelease HistoryDetailsSummary

Released

Conference Paper

Falsification and future performance

MPS-Authors

/persons/resource/persons83792

Balduzzi, D
Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society;

External Resource

https://link.springer.com/content/pdf/10.1007%2F978-3-642-44958-1.pdf
(Publisher version)

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

Fulltext (public)

There are no public fulltexts stored in PuRe

Supplementary Material (public)

There is no public supplementary material available

Citation

Balduzzi, D. (2013). Falsification and future performance. In D. Dowe (Ed.), Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence (pp. 65-78). Berlin, Germany: Springer.

Cite as: https://hdl.handle.net/11858/00-001M-0000-0013-B8D6-8

Abstract

We information-theoretically reformulate two measures of capacity from statistical learning theory: empirical VC-entropy and empirical Rademacher complexity. We show these capacity measures count the number of hypotheses about a dataset that a learning algorithm falsies when it nds the classier in its repertoire minimizing empirical risk. It then follows from that the future performance of predictors on unseen data is controlled in part by how many hypotheses the learner falsies. As a corollary we show that empirical VC-entropy quanties the message length of the true hypothesis in the optimal code of a particular probability distribution, the so-called actual repertoire.