A Distance for HMMs based on Aggregated Wasserstein Metric and State Registration

08/05/2016
by   Yukun Chen, et al.
0

We propose a framework, named Aggregated Wasserstein, for computing a dissimilarity measure or distance between two Hidden Markov Models with state conditional distributions being Gaussian. For such HMMs, the marginal distribution at any time spot follows a Gaussian mixture distribution, a fact exploited to softly match, aka register, the states in two HMMs. We refer to such HMMs as Gaussian mixture model-HMM (GMM-HMM). The registration of states is inspired by the intrinsic relationship of optimal transport and the Wasserstein metric between distributions. Specifically, the components of the marginal GMMs are matched by solving an optimal transport problem where the cost between components is the Wasserstein metric for Gaussian distributions. The solution of the optimization problem is a fast approximation to the Wasserstein metric between two GMMs. The new Aggregated Wasserstein distance is a semi-metric and can be computed without generating Monte Carlo samples. It is invariant to relabeling or permutation of the states. This distance quantifies the dissimilarity of GMM-HMMs by measuring both the difference between the two marginal GMMs and the difference between the two transition matrices. Our new distance is tested on the tasks of retrieval and classification of time series. Experiments on both synthetic data and real data have demonstrated its advantages in terms of accuracy as well as efficiency in comparison with existing distances based on the Kullback-Leibler divergence.

READ FULL TEXT
research
11/12/2017

Aggregated Wasserstein Metric and State Registration for Hidden Markov Models

We propose a framework, named Aggregated Wasserstein, for computing a di...
research
07/26/2022

Sliced Wasserstein Variational Inference

Variational Inference approximates an unnormalized distribution via the ...
research
10/13/2021

Dynamical Wasserstein Barycenters for Time-series Modeling

Many time series can be modeled as a sequence of segments representing h...
research
02/10/2018

Learning to Recommend via Inverse Optimal Matching

We consider recommendation in the context of optimal matching, i.e., we ...
research
12/30/2022

Estimating Latent Population Flows from Aggregated Data via Inversing Multi-Marginal Optimal Transport

We study the problem of estimating latent population flows from aggregat...
research
12/15/2018

Mapper Comparison with Wasserstein Metrics

The challenge of describing model drift is an open question in unsupervi...
research
02/21/2017

Differential Geometric Retrieval of Deep Features

Comparing images to recommend items from an image-inventory is a subject...

Please sign up or login with your details

Forgot password? Click here to reset