Spectral learning of mixtures of Hidden Markov Models

In this work, we propose a novel approach for clustering Hidden Markov Models (HMMs). We use spectral learning for latent variable models to learn HMM parameters in each cluster. Unlike conventional expectation-maximization algorithms, spectral learning enables us to do parameter estimation in latent variable models without iterating, in local optima free fashion. For this reason, our algorithm is computationally cheaper than clustering HMMs with conventional approaches such as EM.