Learning Hidden Markov Models for Regression using Path Aggregation

TL;DR

This paper introduces a method for learning hidden Markov models tailored for regression tasks, jointly inferring model structure and parameters while mapping path features to continuous responses, validated on synthetic and biological data.

Contribution

It presents a novel approach that combines HMM structure learning with regression modeling for sequential data, improving predictive performance.

Findings

Joint learning enhances regression accuracy.

Method performs well on synthetic data.

Effective in biological domain applications.

Abstract

We consider the task of learning mappings from sequential data to real-valued responses. We present and evaluate an approach to learning a type of hidden Markov model (HMM) for regression. The learning process involves inferring the structure and parameters of a conventional HMM, while simultaneously learning a regression model that maps features that characterize paths through the model to continuous responses. Our results, in both synthetic and biological domains, demonstrate the value of jointly learning the two components of our approach.