Median-truncated gradient descent: a robust and scalable nonconvex approach for signal estimation

DOI10.1007/978-3-319-73074-5_8MaRDI QIDQ3296183zbMATH OpenOpenAlexFDO

Authors Yuejie Chi, Yuan-Xin Li, Huishuai Zhang, Yingbin Liang

Publication date 7 July 2020

Published in Applied and Numerical Harmonic Analysis (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/978-3-319-73074-5_8

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12) Nonconvex programming, global optimization (90C26)

Recommendations

• Non-convex low-rank matrix recovery with arbitrary outliers via median-truncated gradient descent
• Efficient learning with robust gradient descent
• Robust estimation via generalized quasi-gradients
• Fast, robust and non-convex subspace recovery
• A well-tempered landscape for non-convex robust subspace recovery

Cites work

• A geometric analysis of phase retrieval
• A nonconvex approach for phase retrieval: reshaped Wirtinger flow and incremental algorithms
• Blind Recovery of Sparse Signals From Subsampled Convolution
• Complete Dictionary Recovery Over the Sphere I: Overview and the Geometric Picture
• Compressive principal component pursuit
• Deterministic guarantees for Burer-Monteiro factorizations of smooth semidefinite programs
• Estimation of (near) low-rank matrices with noise and high-dimensional scaling
• Exact and Stable Covariance Estimation From Quadratic Sampling via Convex Programming
• Exact matrix completion via convex optimization
• Finding low-rank solutions via nonconvex matrix factorization, efficiently and provably
• Gradient descent with random initialization: fast global convergence for nonconvex phase retrieval
• Guaranteed Matrix Completion via Non-Convex Factorization
• Guaranteed minimum-rank solutions of linear matrix equations via nuclear norm minimization
• Guarantees of Riemannian optimization for low rank matrix recovery
• Implicit regularization in nonconvex statistical estimation: gradient descent converges linearly for phase retrieval, matrix completion, and blind deconvolution
• Low-Rank Positive Semidefinite Matrix Recovery From Corrupted Rank-One Measurements
• Low-rank matrix completion using alternating minimization
• Matrix Completion From a Few Entries
• Median-Truncated Nonconvex Approach for Phase Retrieval With Outliers
• Nonconvex Optimization Meets Low-Rank Matrix Factorization: An Overview
• Nonconvex phase synchronization
• On k-Median clustering in high dimensions
• Phase Retrieval Using Alternating Minimization
• Phase retrieval via Wirtinger flow: theory and algorithms
• Phaselift is robust to a constant fraction of arbitrary errors
• Rapid, robust, and reliable blind deconvolution via nonconvex optimization
• Recovering Low-Rank Matrices From Few Coefficients in Any Basis
• Robust Spectral Compressed Sensing via Structured Matrix Completion
• Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems
• Solving Systems of Random Quadratic Equations via Truncated Amplitude Flow
• Symmetry, Saddle Points, and Global Optimization Landscape of Nonconvex Matrix Factorization
• The projected power method: an efficient algorithm for joint alignment from pairwise differences
• Tight Oracle Inequalities for Low-Rank Matrix Recovery From a Minimal Number of Noisy Random Measurements

Cited in

(3)

• Randomized Kaczmarz in adversarial distributed setting
• Non-convex low-rank matrix recovery with arbitrary outliers via median-truncated gradient descent
• Quantile-based iterative methods for corrupted systems of linear equations

Describes a project that uses

Uses Software

• Wirtinger Flow

This page was built for publication: Median-truncated gradient descent: a robust and scalable nonconvex approach for signal estimation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3296183)