paper-with-me

홈 › Papers

Deep Poisson gamma dynamical systems

2018-10-26 · NeurIPS 2018 12 · Dandan Guo, Bo Chen, Hao Zhang, Mingyuan Zhou

We develop deep Poisson-gamma dynamical systems (DPGDS) to model sequentially observed multivariate count data, improving previously proposed models by not only mining deep hierarchical latent structure from the data, but also capturing both first-order and long-range temporal dependencies. Using sophisticated but simple-to-implement data augmentation techniques, we derived closed-form Gibbs sampling update equations by first backward and upward propagating auxiliary latent counts, and then forward and downward sampling latent variables. Moreover, we develop stochastic gradient MCMC inference that is scalable to very long multivariate count time series. Experiments on both synthetic and a variety of real-world data demonstrate that the proposed model not only has excellent predictive performance, but also provides highly interpretable multilayer latent structure to represent hierarchical and temporal information propagation.

📄 PDF Abstract BibTeX arXiv:1810.11209

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationTime SeriesTime Series Analysis

Similar Papers 제목 키워드 기반

Poisson-Gamma dynamical systems

2016-12-01 · NeurIPS 2016 12 · Aaron Schein, Hanna Wallach, Mingyuan Zhou

This paper presents a dynamical system based on the Poisson-Gamma construction for sequentially observed multivariate count data. Inherent to the model is a novel Bayesian nonparametric prior that ties and shrinks param…

Inductive Bias

Poisson-Randomized Gamma Dynamical Systems

2019-10-28 · NeurIPS 2019 12 · Aaron Schein, Scott W. Linderman, Mingyuan Zhou, David M. Blei 외

This paper presents the Poisson-randomized gamma dynamical system (PRGDS), a model for sequentially observed count tensors that encodes a strong inductive bias toward sparsity and burstiness. The PRGDS is based on a new …

Inductive Bias

Poisson--Gamma Dynamical Systems

2017-01-19 · Aaron Schein, Mingyuan Zhou, Hanna Wallach

We introduce a new dynamical system for sequentially observed multivariate count data. This model is based on the gamma--Poisson construction---a natural choice for count data---and relies on a novel Bayesian nonparametr…

Inductive Bias

Nonparametric Bayesian Sparse Graph Linear Dynamical Systems

2018-02-21 · Rahi Kalantari, Joydeep Ghosh, Mingyuan Zhou

A nonparametric Bayesian sparse graph linear dynamical system (SGLDS) is proposed to model sequentially observed multivariate data. SGLDS uses the Bernoulli-Poisson link together with a gamma process to generate an infin…

Time SeriesTime Series Analysis

Bidirectional Convolutional Poisson Gamma Dynamical Systems

2020-12-01 · NeurIPS 2020 12 · Wenchao Chen, Chaojie Wang, Bo Chen, Yicheng Liu 외

Incorporating the natural document-sentence-word structure into hierarchical Bayesian modeling, we propose convolutional Poisson gamma dynamical systems (PGDS) that introduce not only word-level probabilistic convolution…

Bayesian InferenceSentenceVariational Inference