Multinomial Sampling of Latent Variables for Hierarchical Change-Point Detection Articles uri icon

publication date

  • October 2021

start page

  • 215

end page

  • 227

volume

  • 94

International Standard Serial Number (ISSN)

  • 1939-8018

Electronic International Standard Serial Number (EISSN)

  • 1939-8115

abstract

  • Bayesian change-point detection, with latent variable models, allows to perform segmentation of high-dimensional time-series with heterogeneous statistical nature. We assume that change-points lie on a lower-dimensional manifold where we aim to infer a discrete representation via subsets of latent variables. For this particular model, full inference is computationally unfeasible and pseudo-observations based on point-estimates of latent variables are used instead. However, if their estimation is not certain enough, change-point detection gets affected. To circumvent this problem, we propose a multinomial sampling methodology that improves the detection rate and reduces the delay while keeping complexity stable and inference analytically tractable. Our experiments show results that outperform the baseline method and we also provide an example oriented to a human behavioral study.

keywords

  • bayesian inference; change-point detection (cpd); latent variable models; multinomial likelihoods