Convergence Rates for Gaussian Mixtures of Experts

07/09/2019
by   Nhat Ho, et al.
6

We provide a theoretical treatment of over-specified Gaussian mixtures of experts with covariate-free gating networks. We establish the convergence rates of the maximum likelihood estimation (MLE) for these models. Our proof technique is based on a novel notion of algebraic independence of the expert functions. Drawing on optimal transport theory, we establish a connection between the algebraic independence and a certain class of partial differential equations (PDEs). Exploiting this connection allows us to derive convergence rates and minimax lower bounds for parameter estimation.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset