Show simple item record

dc.contributor.advisorKeyes, David E.
dc.contributor.authorChen, Yuxin
dc.date.accessioned2015-05-14T18:41:11Z
dc.date.available2015-05-14T18:41:11Z
dc.date.issued2015-05-14
dc.identifier.doi10.25781/KAUST-YPTCX
dc.identifier.urihttp://hdl.handle.net/10754/552902
dc.description.abstractThis work considers black-box Bayesian inference over high-dimensional parameter spaces. The well-known and widely respected adaptive Metropolis (AM) algorithm is extended herein to asymptotically scale uniformly with respect to the underlying parameter dimension, by respecting the variance, for Gaussian targets. The result- ing algorithm, referred to as the dimension-independent adaptive Metropolis (DIAM) algorithm, also shows improved performance with respect to adaptive Metropolis on non-Gaussian targets. This algorithm is further improved, and the possibility of probing high-dimensional targets is enabled, via GPU-accelerated numerical libraries and periodically synchronized concurrent chains (justified a posteriori). Asymptoti- cally in dimension, this massively parallel dimension-independent adaptive Metropolis (MPDIAM) GPU implementation exhibits a factor of four improvement versus the CPU-based Intel MKL version alone, which is itself already a factor of three improve- ment versus the serial version. The scaling to multiple CPUs and GPUs exhibits a form of strong scaling in terms of the time necessary to reach a certain convergence criterion, through a combination of longer time per sample batch (weak scaling) and yet fewer necessary samples to convergence. This is illustrated by e ciently sampling from several Gaussian and non-Gaussian targets for dimension d 1000.
dc.language.isoen
dc.subjectMarkov chain Monte Carlo
dc.subjectbayesian interference
dc.subjectadaptive metropolis
dc.subjectmetropolis hastings
dc.subjectparallele processing
dc.subjectGPM acceleration
dc.titleMassively Parallel Dimension Independent Adaptive Metropolis
dc.typeThesis
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
thesis.degree.grantorKing Abdullah University of Science and Technology
dc.contributor.committeememberMoshkov, Mikhail
dc.contributor.committeememberGao, Xin
thesis.degree.disciplineComputer Science
thesis.degree.nameMaster of Science
refterms.dateFOA2018-06-14T07:47:12Z


Files in this item

Thumbnail
Name:
Thesis.pdf
Size:
3.325Mb
Format:
PDF

This item appears in the following Collection(s)

Show simple item record