Rademacher complexity and grammar induction algorithms: what it may (not) tell us

Authors:
Sophia Katrenko;Menno van Zaanen
Affiliations:
Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands;TiCC, Tilburg University, Tilburg, The Netherlands
Venue:
ICGI'10 Proceedings of the 10th international colloquium conference on Grammatical inference: theoretical results and applications
Year:
2010

Citing 3
Cited 0

Rademacher and gaussian complexities: risk bounds and structural results

The Journal of Machine Learning Research
Problems with Evaluation of Unsupervised Empirical Grammatical Inference Systems

ICGI '08 Proceedings of the 9th international colloquium on Grammatical Inference: Algorithms and Applications
Nearest Neighbor Clustering: A Baseline Method for Consistent Clustering with Arbitrary Objective Functions

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper revisits a problem of the evaluation of computational grammatical inference (GI) systems and discusses what role complexity measures can play for the assessment of GI. We provide a motivation for using the Rademacher complexity and give an example showing how this complexity measure can be used in practice.