DeepAI AI Chat
Log In Sign Up

Poisson-Randomized Gamma Dynamical Systems

by   Aaron Schein, et al.

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 motif in Bayesian latent variable modeling, an alternating chain of discrete Poisson and continuous gamma latent states that is analytically convenient and computationally tractable. This motif yields closed-form complete conditionals for all variables by way of the Bessel distribution and a novel discrete distribution that we call the shifted confluent hypergeometric distribution. We draw connections to closely related models and compare the PRGDS to these models in studies of real-world count data sets of text, international events, and neural spike trains. We find that a sparse variant of the PRGDS, which allows the continuous gamma latent states to take values of exactly zero, often obtains better predictive performance than other models and is uniquely capable of inferring latent structures that are highly localized in time.


Poisson--Gamma Dynamical Systems

We introduce a new dynamical system for sequentially observed multivaria...

Nonparametric Bayesian Factor Analysis for Dynamic Count Matrices

A gamma process dynamic Poisson factor analysis model is proposed to fac...

Deep Poisson gamma dynamical systems

We develop deep Poisson-gamma dynamical systems (DPGDS) to model sequent...

Nonparametric Bayesian Sparse Graph Linear Dynamical Systems

A nonparametric Bayesian sparse graph linear dynamical system (SGLDS) is...

Hierarchical Compound Poisson Factorization

Non-negative matrix factorization models based on a hierarchical Gamma-P...

A time-dependent Poisson-Gamma model for recruitment forecasting in multicenter studies

Forecasting recruitments is a key component of the monitoring phase of m...

Models Based on Exponential Interarrival Times for Single-Unusual-Event Count Data

At least one unusual event appears in some count datasets. It will lead ...