Log In Sign Up

Generative Principal Component Analysis

by   Zhaoqiang Liu, et al.

In this paper, we study the problem of principal component analysis with generative modeling assumptions, adopting a general model for the observed matrix that encompasses notable special cases, including spiked matrix recovery and phase retrieval. The key assumption is that the underlying signal lies near the range of an L-Lipschitz continuous generative model with bounded k-dimensional inputs. We propose a quadratic estimator, and show that it enjoys a statistical rate of order √(klog L/m), where m is the number of samples. We also provide a near-matching algorithm-independent lower bound. Moreover, we provide a variant of the classic power method, which projects the calculated data onto the range of the generative model during each iteration. We show that under suitable conditions, this method converges exponentially fast to a point achieving the above-mentioned statistical rate. We perform experiments on various image datasets for spiked matrix and phase retrieval models, and illustrate performance gains of our method to the classic power method and the truncated power method devised for sparse principal component analysis.


page 23

page 25


Diffusion Approximations for Online Principal Component Estimation and Global Convergence

In this paper, we propose to adopt the diffusion approximation tools to ...

Misspecified Phase Retrieval with Generative Priors

In this paper, we study phase retrieval under model misspecification and...

A Framework for Private Matrix Analysis

We study private matrix analysis in the sliding window model where only ...

Nonasymptotic Guarantees for Low-Rank Matrix Recovery with Generative Priors

Many problems in statistics and machine learning require the reconstruct...

The spiked matrix model with generative priors

Using a low-dimensional parametrization of signals is a generic and powe...

High-dimensional principal component analysis with heterogeneous missingness

We study the problem of high-dimensional Principal Component Analysis (P...