Saved in:
Bibliographic Details
Main Authors: Liu, Zhaoqiang, Li, Wen, Chen, Junren
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.01326
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915003164000256
author Liu, Zhaoqiang
Li, Wen
Chen, Junren
author_facet Liu, Zhaoqiang
Li, Wen
Chen, Junren
contents Generalized eigenvalue problems (GEPs) find applications in various fields of science and engineering. For example, principal component analysis, Fisher's discriminant analysis, and canonical correlation analysis are specific instances of GEPs and are widely used in statistical data processing. In this work, we study GEPs under generative priors, assuming that the underlying leading generalized eigenvector lies within the range of a Lipschitz continuous generative model. Under appropriate conditions, we show that any optimal solution to the corresponding optimization problems attains the optimal statistical rate. Moreover, from a computational perspective, we propose an iterative algorithm called the Projected Rayleigh Flow Method (PRFM) to approximate the optimal solution. We theoretically demonstrate that under suitable assumptions, PRFM converges linearly to an estimated vector that achieves the optimal statistical rate. Numerical results are provided to demonstrate the effectiveness of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2411_01326
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generalized Eigenvalue Problems with Generative Priors
Liu, Zhaoqiang
Li, Wen
Chen, Junren
Machine Learning
Generalized eigenvalue problems (GEPs) find applications in various fields of science and engineering. For example, principal component analysis, Fisher's discriminant analysis, and canonical correlation analysis are specific instances of GEPs and are widely used in statistical data processing. In this work, we study GEPs under generative priors, assuming that the underlying leading generalized eigenvector lies within the range of a Lipschitz continuous generative model. Under appropriate conditions, we show that any optimal solution to the corresponding optimization problems attains the optimal statistical rate. Moreover, from a computational perspective, we propose an iterative algorithm called the Projected Rayleigh Flow Method (PRFM) to approximate the optimal solution. We theoretically demonstrate that under suitable assumptions, PRFM converges linearly to an estimated vector that achieves the optimal statistical rate. Numerical results are provided to demonstrate the effectiveness of the proposed method.
title Generalized Eigenvalue Problems with Generative Priors
topic Machine Learning
url https://arxiv.org/abs/2411.01326