Saved in:
Bibliographic Details
Main Authors: Wang, Jiahao, Yang, Sikun, Koeppl, Heinz, Cheng, Xiuzhen, Hu, Pengfei, Zhang, Guoming
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2402.16297
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914806314827776
author Wang, Jiahao
Yang, Sikun
Koeppl, Heinz
Cheng, Xiuzhen
Hu, Pengfei
Zhang, Guoming
author_facet Wang, Jiahao
Yang, Sikun
Koeppl, Heinz
Cheng, Xiuzhen
Hu, Pengfei
Zhang, Guoming
contents Probabilistic approaches for handling count-valued time sequences have attracted amounts of research attentions because their ability to infer explainable latent structures and to estimate uncertainties, and thus are especially suitable for dealing with \emph{noisy} and \emph{incomplete} count data. Among these models, Poisson-Gamma Dynamical Systems (PGDSs) are proven to be effective in capturing the evolving dynamics underlying observed count sequences. However, the state-of-the-art PGDS still fails to capture the \emph{time-varying} transition dynamics that are commonly observed in real-world count time sequences. To mitigate this gap, a non-stationary PGDS is proposed to allow the underlying transition matrices to evolve over time, and the evolving transition matrices are modeled by sophisticatedly-designed Dirichlet Markov chains. Leveraging Dirichlet-Multinomial-Beta data augmentation techniques, a fully-conjugate and efficient Gibbs sampler is developed to perform posterior simulation. Experiments show that, in comparison with related models, the proposed non-stationary PGDS achieves improved predictive performance due to its capacity to learn non-stationary dependency structure captured by the time-evolving transition matrices.
format Preprint
id arxiv_https___arxiv_org_abs_2402_16297
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics
Wang, Jiahao
Yang, Sikun
Koeppl, Heinz
Cheng, Xiuzhen
Hu, Pengfei
Zhang, Guoming
Machine Learning
Artificial Intelligence
Probabilistic approaches for handling count-valued time sequences have attracted amounts of research attentions because their ability to infer explainable latent structures and to estimate uncertainties, and thus are especially suitable for dealing with \emph{noisy} and \emph{incomplete} count data. Among these models, Poisson-Gamma Dynamical Systems (PGDSs) are proven to be effective in capturing the evolving dynamics underlying observed count sequences. However, the state-of-the-art PGDS still fails to capture the \emph{time-varying} transition dynamics that are commonly observed in real-world count time sequences. To mitigate this gap, a non-stationary PGDS is proposed to allow the underlying transition matrices to evolve over time, and the evolving transition matrices are modeled by sophisticatedly-designed Dirichlet Markov chains. Leveraging Dirichlet-Multinomial-Beta data augmentation techniques, a fully-conjugate and efficient Gibbs sampler is developed to perform posterior simulation. Experiments show that, in comparison with related models, the proposed non-stationary PGDS achieves improved predictive performance due to its capacity to learn non-stationary dependency structure captured by the time-evolving transition matrices.
title A Poisson-Gamma Dynamic Factor Model with Time-Varying Transition Dynamics
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2402.16297