Black-Box $k$-to-$1$-PCA Reductions: Theory and Applications

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jambulapati, Arun, Kumar, Syamantak, Li, Jerry, Pandey, Shourya, Pensia, Ankit, Tian, Kevin
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916282309279744
author Jambulapati, Arun
Kumar, Syamantak
Li, Jerry
Pandey, Shourya
Pensia, Ankit
Tian, Kevin
author_facet Jambulapati, Arun
Kumar, Syamantak
Li, Jerry
Pandey, Shourya
Pensia, Ankit
Tian, Kevin
contents The $k$-principal component analysis ($k$-PCA) problem is a fundamental algorithmic primitive that is widely-used in data analysis and dimensionality reduction applications. In statistical settings, the goal of $k$-PCA is to identify a top eigenspace of the covariance matrix of a distribution, which we only have black-box access to via samples. Motivated by these settings, we analyze black-box deflation methods as a framework for designing $k$-PCA algorithms, where we model access to the unknown target matrix via a black-box $1$-PCA oracle which returns an approximate top eigenvector, under two popular notions of approximation. Despite being arguably the most natural reduction-based approach to $k$-PCA algorithm design, such black-box methods, which recursively call a $1$-PCA oracle $k$ times, were previously poorly-understood. Our main contribution is significantly sharper bounds on the approximation parameter degradation of deflation methods for $k$-PCA. For a quadratic form notion of approximation we term ePCA (energy PCA), we show deflation methods suffer no parameter loss. For an alternative well-studied approximation notion we term cPCA (correlation PCA), we tightly characterize the parameter regimes where deflation methods are feasible. Moreover, we show that in all feasible regimes, $k$-cPCA deflation algorithms suffer no asymptotic parameter loss for any constant $k$. We apply our framework to obtain state-of-the-art $k$-PCA algorithms robust to dataset contamination, improving prior work in sample complexity by a $\mathsf{poly}(k)$ factor.
format Preprint
id arxiv_https___arxiv_org_abs_2403_03905
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Black-Box $k$-to-$1$-PCA Reductions: Theory and Applications
Jambulapati, Arun
Kumar, Syamantak
Li, Jerry
Pandey, Shourya
Pensia, Ankit
Tian, Kevin
Numerical Analysis
Data Structures and Algorithms
Machine Learning
The $k$-principal component analysis ($k$-PCA) problem is a fundamental algorithmic primitive that is widely-used in data analysis and dimensionality reduction applications. In statistical settings, the goal of $k$-PCA is to identify a top eigenspace of the covariance matrix of a distribution, which we only have black-box access to via samples. Motivated by these settings, we analyze black-box deflation methods as a framework for designing $k$-PCA algorithms, where we model access to the unknown target matrix via a black-box $1$-PCA oracle which returns an approximate top eigenvector, under two popular notions of approximation. Despite being arguably the most natural reduction-based approach to $k$-PCA algorithm design, such black-box methods, which recursively call a $1$-PCA oracle $k$ times, were previously poorly-understood. Our main contribution is significantly sharper bounds on the approximation parameter degradation of deflation methods for $k$-PCA. For a quadratic form notion of approximation we term ePCA (energy PCA), we show deflation methods suffer no parameter loss. For an alternative well-studied approximation notion we term cPCA (correlation PCA), we tightly characterize the parameter regimes where deflation methods are feasible. Moreover, we show that in all feasible regimes, $k$-cPCA deflation algorithms suffer no asymptotic parameter loss for any constant $k$. We apply our framework to obtain state-of-the-art $k$-PCA algorithms robust to dataset contamination, improving prior work in sample complexity by a $\mathsf{poly}(k)$ factor.
title Black-Box $k$-to-$1$-PCA Reductions: Theory and Applications
topic Numerical Analysis
Data Structures and Algorithms
Machine Learning
url https://arxiv.org/abs/2403.03905