Provable ICA with Unknown Gaussian Noise, and Implications for Gaussian Mixtures and Autoencoders

Abstract

We present a new algorithm for Independent Component Analysis (ICA) which has provable performance guarantees. In particular, suppose we are given samples of the form $y = Ax + η$ where $A$ is an unknown $n \times n$ matrix and $x$ is a random variable whose components are independent and have a fourth moment strictly less than that of a standard Gaussian random variable and $η$ is an $n$-dimensional Gaussian random variable with unknown covariance $Σ$: We give an algorithm that provable recovers $A$ and $Σ$ up to an additive $ε$ and whose running time and sample complexity are polynomial in $n$ and $1 / ε$. To accomplish this, we introduce a novel "quasi-whitening" step that may be useful in other contexts in which the covariance of Gaussian noise is not known in advance. We also give a general framework for finding all local optima of a function (given an oracle for approximately finding just one) and this is a crucial step in our algorithm, one that has been overlooked in previous attempts, and allows us to control the accumulation of error when we find the columns of $A$ one by one via local search.