Search Machine Learning Repository: Spectral Experts for Estimating Mixtures of Linear Regressions
Authors: Arun T. Chaganty and Percy Liang
Conference: Proceedings of the 30th International Conference on Machine Learning (ICML-13)
Year: 2013
Pages: 1040-1048
Abstract: Discriminative latent-variable models are typically learned using EM or gradient-based optimization, which suffer from local optima. In this paper, we develop a new computationally efficient and provably consistent estimator for the mixture of linear regressions, a simple instance of discriminative latent-variable models. Our approach relies on a low-rank linear regression to recover a symmetric tensor, which can be factorized into the parameters using the tensor power method. We prove rates of convergence for our estimator and provide an empirical evaluation illustrating its strengths relative to local optimization (EM).
[pdf] [BibTeX]

authors venues years
Suggest Changes to this paper.
Brought to you by the WUSTL Machine Learning Group. We have open faculty positions (tenured and tenure-track).