Infinite Mixture Model of Markov Chains

06/19/2017
by   Jan Reubold, et al.
0

We propose a Bayesian nonparametric mixture model for prediction- and information extraction tasks with an efficient inference scheme. It models categorical-valued time series that exhibit dynamics from multiple underlying patterns (e.g. user behavior traces). We simplify the idea of capturing these patterns by hierarchical hidden Markov models (HHMMs) - and extend the existing approaches by the additional representation of structural information. Our empirical results are based on both synthetic- and real world data. They indicate that the results are easily interpretable, and that the model excels at segmentation and prediction performance: it successfully identifies the generating patterns and can be used for effective prediction of future observations.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/05/2012

Infinite Shift-invariant Grouped Multi-task Learning for Gaussian Processes

Multi-task learning leverages shared information among data sets to impr...
research
02/20/2016

The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM

We propose the segmented iHMM (siHMM), a hierarchical infinite hidden Ma...
research
05/03/2015

A Linear-Time Particle Gibbs Sampler for Infinite Hidden Markov Models

Infinite Hidden Markov Models (iHMM's) are an attractive, nonparametric ...
research
09/04/2018

Music Sequence Prediction with Mixture Hidden Markov Models

Recommendation systems that automatically generate personalized music pl...
research
12/31/2014

Detailed Derivations of Small-Variance Asymptotics for some Hierarchical Bayesian Nonparametric Models

In this note we provide detailed derivations of two versions of small-va...
research
10/28/2019

Large-Scale Characterization and Segmentation of Internet Path Delays with Infinite HMMs

Round-Trip Times are one of the most commonly collected performance metr...
research
10/25/2021

On Learning Prediction-Focused Mixtures

Probabilistic models help us encode latent structures that both model th...

Please sign up or login with your details

Forgot password? Click here to reset