White Rose University Consortium logo
University of Leeds logo University of Sheffield logo York University logo

Parameter estimation in stochastic logic programs

Cussens, J. (2001) Parameter estimation in stochastic logic programs. Machine Learning, 44 (3). pp. 245-271. ISSN 0885-6125

Full text not available from this repository.

Abstract

Stochastic logic programs (SLPs) are logic programs with parameterised clauses which define a log-linear distribution over refutations of goals. The log-linear distribution provides, by marginalisation, a distribution over variable bindings, allowing SLPs to compactly represent quite complex distributions. We analyse the fundamental statistical properties of SLPs addressing issues concerning infinite derivations, 'unnormalised SLPs and impure SLPs. After detailing existing approaches to parameter estimation for log-linear models and their application to SLPs, we present a new algorithm called failure-adjusted maximisation (FAM). FAM is an instance of the EM algorithm that applies specifically to normalised SLPs and provides a closed-form for computing parameter updates within an iterative maximisation approach. We empirically show that FAM works on some small examples and discuss methods for applying it to bigger problems.

Item Type: Article
Institution: The University of York
Academic Units: The University of York > Computer Science (York)
Depositing User: York RAE Import
Date Deposited: 30 Mar 2009 08:36
Last Modified: 30 Mar 2009 08:36
Published Version: http://dx.doi.org/10.1023/A:1010924021315
Status: Published
Publisher: Springer Verlag
Identification Number: 10.1023/A:1010924021315
URI: http://eprints.whiterose.ac.uk/id/eprint/6983

Actions (repository staff only: login required)