de.mpg.escidoc.pubman.appbase.FacesBean
English
 
Help Guide Disclaimer Contact us Login
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Conference Paper

Falsification and future performance

MPS-Authors
http://pubman.mpdl.mpg.de/cone/persons/resource/persons83792

Balduzzi,  D
Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society;

Locator
There are no locators available
Fulltext (public)
There are no public fulltexts available
Supplementary Material (public)
There is no public supplementary material available
Citation

Balduzzi, D. (2011). Falsification and future performance. In Solomonoff 85th Memorial Conference (pp. 1-13). Berlin, Germany: Springer.


Cite as: http://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.