Stochastic Variational Inference for Hidden Markov Models

TL;DR

This paper introduces a stochastic variational inference algorithm tailored for hidden Markov models, effectively handling dependencies in sequential data and enabling scalable analysis of large datasets.

Contribution

The authors develop a novel SVI algorithm for HMMs that accounts for chain dependencies using adaptive error bounding, extending stochastic inference to time-dependent data.

Findings

Effective on synthetic data

Scalable to large genomics datasets

Handles chain dependencies with adaptive bounds

Abstract

Variational inference algorithms have proven successful for Bayesian analysis in large data settings, with recent advances using stochastic variational inference (SVI). However, such methods have largely been studied in independent or exchangeable data settings. We develop an SVI algorithm to learn the parameters of hidden Markov models (HMMs) in a time-dependent data setting. The challenge in applying stochastic optimization in this setting arises from dependencies in the chain, which must be broken to consider minibatches of observations. We propose an algorithm that harnesses the memory decay of the chain to adaptively bound errors arising from edge effects. We demonstrate the effectiveness of our algorithm on synthetic experiments and a large genomics dataset where a batch algorithm is computationally infeasible.