Robust learning of inhomogeneous PMMs

Show simple item record

dc.contributor University of Helsinki, Helsinki Institute for Information Technology en
dc.contributor University of Helsinki, Department of Computer Science en
dc.contributor University of Helsinki, Department of Computer Science en
dc.contributor.author Eggeling, Ralf
dc.contributor.author Roos, Teemu
dc.contributor.author Myllymäki, Petri
dc.contributor.author Grosse, Ivo
dc.contributor.editor Kaski, Samuel
dc.contributor.editor Corander, Jukka
dc.date.accessioned 2015-02-03T13:16:17Z
dc.date.available 2015-02-03T13:16:17Z
dc.date.issued 2014-04
dc.identifier.citation Eggeling , R , Roos , T , Myllymäki , P & Grosse , I 2014 , Robust learning of inhomogeneous PMMs . in S Kaski & J Corander (eds) , Proceedings of the 17th International Conference on Artificial Intelligence and Statistics (AISTATS-2014) . JMLR: Workshop and Conference Proceedings , vol. 33 , pp. 229-237 , International Conference on Artificial Intelligence and Statistics , Reykjavik , Iceland , 22/04/2014 . < http://jmlr.org/proceedings/papers/v33/ > en
dc.identifier.citation conference en
dc.identifier.other PURE: 35926940
dc.identifier.other PURE UUID: af98d5f1-f4b2-4777-98a5-8081fc3d2b31
dc.identifier.other Scopus: 84946570338
dc.identifier.other ORCID: /0000-0001-9095-282X/work/32631090
dc.identifier.other ORCID: /0000-0002-3583-1029/work/29571046
dc.identifier.other ORCID: /0000-0001-9470-3759/work/30807021
dc.identifier.uri http://hdl.handle.net/10138/153190
dc.description.abstract Inhomogeneous parsimonious Markov models have recently been introduced for modeling symbolic sequences, with a main application being DNA sequence analysis. Structure and parameter learning of these models has been proposed using a Bayesian approach, which entails the practically challenging choice of the prior distribution. Cross validation is a possible way of tuning the prior hyperparameters towards a specific task such as prediction or classification, but it is overly time-consuming. On this account, robust learning methods, which do not require explicit prior specification and – in the absence of prior knowledge – no hyperparameter tuning, are of interest. In this work, we empirically investigate the performance of robust alternatives for structure and parameter learning that extend the practical applicability of parsimonious Markov models to more complex settings than before. en
dc.format.extent 9
dc.language.iso eng
dc.relation.ispartof Proceedings of the 17th International Conference on Artificial Intelligence and Statistics (AISTATS-2014)
dc.relation.ispartofseries JMLR: Workshop and Conference Proceedings
dc.relation.uri http://jmlr.org/proceedings/papers/v33/
dc.rights en
dc.subject 113 Computer and information sciences en
dc.title Robust learning of inhomogeneous PMMs en
dc.type Conference contribution
dc.type.uri info:eu-repo/semantics/other
dc.contributor.pbl
dc.contributor.pbl
dc.contributor.pbl
dc.contributor.pbl
dc.contributor.pbl
dc.contributor.pbl

Files in this item

Total number of downloads: Loading...

Files Size Format View
Robust_PMM_AISTATS.pdf 276.4Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record