Abstract

Learning Diagonal Gaussian Mixture Models and Incomplete Tensor Decompositions

Jiawang Nie
University of California, San Diego (UCSD)

This talk discusses how to learn parameters in diagonal Gaussian mixture models. The problem can be formulated as computing incomplete symmetric tensor decompositions. We use generating polynomials to compute incomplete symmetric tensor decompositions and approximations. Then the tensor approximation method is used to learn diagonal Gaussian mixture models. We also do the stability analysis. When the first and third order moments are sufficiently accurate, we show that the obtained parameters for the Gaussian mixture models are also highly accurate. This is a joint work with Bingni Guo and Zi Yang.