Home > Research > Publications & Outputs > Fast nonparametric clustering of structured tim...

Links

Text available via DOI:

View graph of relations

Fast nonparametric clustering of structured time-series

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published
  • James Hensman
  • Magnus Rattray
  • Neil D. Lawrence
Close
Article number6802369
<mark>Journal publication date</mark>1/02/2015
<mark>Journal</mark>IEEE Transactions on Pattern Analysis and Machine Intelligence
Issue number2
Volume37
Number of pages11
Pages (from-to)383-393
Publication StatusPublished
Early online date18/04/14
<mark>Original language</mark>English

Abstract

In this publication, we combine two Bayesian nonparametric models: the Gaussian Process (GP) and the Dirichlet Process (DP). Our innovation in the GP model is to introduce a variation on the GP prior which enables us to model structured time-series data, i.e., data containing groups where we wish to model inter- and intra-group variability. Our innovation in the DP model is an implementation of a new fast collapsed variational inference procedure which enables us to optimize our variational approximation significantly faster than standard VB approaches. In a biological time series application we show how our model better captures salient features of the data, leading to better consistency with existing biological classifications, while the associated inference algorithm provides a significant speed-up over EM-based variational inference.