Heteroskedastic PCA: Algorithm, Optimality, and Applications

10/19/2018
by   Anru Zhang, et al.
0

Principal component analysis (PCA) and singular value decomposition (SVD) are widely used in statistics, machine learning, and applied mathematics. It has been well studied in the case of homoskedastic noise, where the noise levels of the contamination are homogeneous. In this paper, we consider PCA and SVD in the presence of heteroskedastic noise, which arises naturally in a range of applications. We introduce a general framework for heteroskedastic PCA and propose an algorithm called HeteroPCA, which involves iteratively imputing the diagonal entries to remove the bias due to heteroskedasticity. This procedure is computationally efficient and provably optimal under the generalized spiked covariance model. A key technical step is a deterministic robust perturbation analysis on the singular subspace, which can be of independent interest. The effectiveness of the proposed algorithm is demonstrated in a suite of applications, including heteroskedastic low-rank matrix denoising, Poisson PCA, and SVD based on heteroskedastic and incomplete data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/24/2021

Regularisation for PCA- and SVD-type matrix factorisations

Singular Value Decomposition (SVD) and its close relative, Principal Com...
research
04/07/2022

DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors

DeepTensor is a computationally efficient framework for low-rank decompo...
research
07/15/2023

Identification of Stochasticity by Matrix-decomposition: Applied on Black Hole Data

Timeseries classification as stochastic (noise-like) or non-stochastic (...
research
02/10/2017

PCA in Data-Dependent Noise (Correlated-PCA): Nearly Optimal Finite Sample Guarantees

We study Principal Component Analysis (PCA) in a setting where a part of...
research
02/18/2020

Optimal Structured Principal Subspace Estimation: Metric Entropy and Minimax Rates

Driven by a wide range of applications, many principal subspace estimati...
research
07/27/2023

PCA, SVD, and Centering of Data

The research detailed in this paper scrutinizes Principal Component Anal...
research
05/16/2010

On the Subspace of Image Gradient Orientations

We introduce the notion of Principal Component Analysis (PCA) of image g...

Please sign up or login with your details

Forgot password? Click here to reset