Evidence estimation using stochastic likelihood approximations

dc.contributor.advisorEggers, H. C.en_ZA
dc.contributor.advisorKroon, R. S. (Steve)en_ZA
dc.contributor.authorCameron, Scotten_ZA
dc.contributor.otherStellenbosch University. Faculty of Science. Dept. of Physics.en_ZA
dc.descriptionThesis (MSc)--Stellenbosch University, 2020.en_ZA
dc.description.abstractENGLISH ABSTRACT: We consider the problem of estimating evidence for parametric Bayesian models in the large data regime. Many existing evidence estimation algorithms scale poorly due to their need to repeatedly calculate the exact likelihood, which requires iterating over the entire data set. This inefficiency can be circumvented with the use of stochastic likelihood estimates on small sub-samples of the data set. We therefore tackle this problem by introducing stochastic gradient Monte Carlo methods for evidence estimation, our main contribution being stochastic gradient annealed importance sampling. Our approach enables efficient online evidence estimation for large data sets. SGAIS is considerably faster than previous approaches for single data sets, with improved order complexity for online estimation, without noticeable loss of accuracy.en_ZA
dc.description.sponsorshipThe financial assistance of the National Institute of Theoretical Physics (NITheP) towards this research is hereby acknowledged. Opinions expressed and conclusions arrived at, are those of the author and are not necessarily to be attributed to NITheP.en_ZA
dc.format.extentviii, 86 pagesen_ZA
dc.publisherStellenbosch : Stellenbosch University.en_ZA
dc.subjectEvidence -- Estimationen_ZA
dc.subjectStochastic approximationsen_ZA
dc.subjectParameter estimationen_ZA
dc.subjectSimulated annealing (Mathematics)en_ZA
dc.subjectBig dataen_ZA
dc.titleEvidence estimation using stochastic likelihood approximationsen_ZA
dc.rights.holderStellenbosch University.en_ZA

Files in this item


This item appears in the following Collection(s)