Poster
Global Convergence of Least Squares EM for Demixing Two Log-Concave Densities
Wei Qian · Yuqian Zhang · Yudong Chen
East Exhibition Hall B, C #119
Keywords: [ Non-Convex Optimization ] [ Optimization ] [ Learning Theory ] [ Algorithms -> Density Estimation; Probabilistic Methods -> Latent Variable Models; Theory ]
This work studies the location estimation problem for a mixture of two rotation invariant log-concave densities. We demonstrate that Least Squares EM, a variant of the EM algorithm, converges to the true location parameter from a randomly initialized point. Moreover, we establish the explicit convergence rates and sample complexity bounds, revealing their dependence on the signal-to-noise ratio and the tail property of the log-concave distributions. Our analysis generalizes previous techniques for proving the convergence results of Gaussian mixtures, and highlights that an angle-decreasing property is sufficient for establishing global convergence for Least Squares EM.
Live content is unavailable. Log in and register to view live content