Robust matrix estimations meet Frank-Wolfe algorithm

DOI10.1007/s10994-023-06325-wOpenAlexW4362634707MaRDI QIDQ6134341

Cheng Yong Tang, Naimin Jing, Ethan X. Fang

Publication date: 22 August 2023

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-023-06325-w

zbMATH Keywords

robust statistical methodsHuber lossFrank-Wolfe algorithmsnon-smooth criterion functionmatrix-valued parametersnon-asymptotic properties

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Noisy matrix decomposition via convex relaxation: optimal rates in high dimensions
• Probability in Banach spaces. Isoperimetry and processes
• Estimation of high-dimensional low-rank matrices
• Estimation of (near) low-rank matrices with noise and high-dimensional scaling
• Nuclear-norm penalization and optimal rates for noisy low-rank matrix completion
• A shrinkage principle for heavy-tailed data: high-dimensional robust low-rank matrix recovery
• Multivariate reduced-rank regression
• A Bennett concentration inequality and its application to suprema of empirical processes
• A new perspective on robust \(M\)-estimation: finite sample theory and applications to dependence-adjusted multiple testing
• Robust low-rank matrix estimation
• Statistical consistency and asymptotic normality for high-dimensional robust \(M\)-estimators
• Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence
• Noisy low-rank matrix completion with general sampling distribution
• An Extended Frank--Wolfe Method with “In-Face” Directions, and Its Application to Low-Rank Matrix Completion
• Matrix completion via an alternating direction method
• Adaptive Huber Regression
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• Robust reduced-rank regression
• A Simpler Approach to Matrix Completion
• Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
• New analysis and results for the Frank-Wolfe method
• A unified framework for high-dimensional analysis of \(M\)-estimators with decomposable regularizers

This page was built for publication: Robust matrix estimations meet Frank-Wolfe algorithm