Empirical Inference

Falsification and future performance

2013

Conference Paper

ei


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 falsifies when it finds the classifier 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 falsifies. As a corollary we show that empirical VC-entropy quantifies the message length of the true hypothesis in the optimal code of a particular probability distribution, the so-called actual repertoire.

Author(s): Balduzzi, D.
Book Title: Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence
Volume: 7070
Pages: 65--78
Year: 2013
Month: January
Day: 0
Series: Lecture Notes in Computer Science
Publisher: Springer

Department(s): Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

DOI: 10.1007/978-3-642-44958-1_5
Event Name: Solomonoff 85th Memorial Conference
Event Place: Melbourne, Australia

Address: Berlin, Germany
State: Published

Links: PDF
Web

BibTex

@inproceedings{Balduzzi2011_3,
  title = {Falsification and future performance},
  author = {Balduzzi, D.},
  booktitle = {Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence},
  volume = {7070},
  pages = {65--78},
  series = {Lecture Notes in Computer Science},
  publisher = {Springer},
  address = {Berlin, Germany},
  month = jan,
  year = {2013},
  doi = {10.1007/978-3-642-44958-1_5},
  month_numeric = {1}
}