Provable ICA with Unknown Gaussian Noise, and Implications for Gaussian Mixtures and Autoencoders
Name
453_2015_9972_ReferencePDF.pdf
Size
271.64 KB
Format
Adobe PDF
Checksum (MD5)
a07a192eec0e0b5fc335e404ea5c9d3e
Author(s)
Arora, Sanjeev
Ge, Rong
Moitra, Ankur
Sachdeva, Sushant
Date Issued
March 2015
Journal
Algorithmica
Publisher
Springer US
Citation
Arora, Sanjeev, Rong Ge, Ankur Moitra, and Sushant Sachdeva. “Provable ICA with Unknown Gaussian Noise, and Implications for Gaussian Mixtures and Autoencoders.” Algorithmica 72, no. 1 (March 4, 2015): 215–236.
Version
Author's final manuscript
Abstract
We present a new algorithm for independent component analysis which has provable performance guarantees. In particular, suppose we are given samples of the form y=Ax+η where A is an unknown but non-singular n×n matrix, x is a random variable whose coordinates are independent and have a fourth order 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 provably recovers A and Σ up to an additive ϵϵ 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 applications where there is additive Gaussian noise whose covariance is unknown. 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.
MIT Department
Massachusetts Institute of Technology. Department of Mathematics
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/s00453-015-9972-2
