Multilinear Compressive Sensing and an Application to Convolutional Linear Networks

DOI10.1137/18M119834XMaRDI QIDQ5025785

François Malgouyres, Joseph M. Landsberg

Publication date: 3 February 2022

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1703.08044

zbMATH Keywords

matrix factorizationconvolutional networksstable recoveryinterpretable learningdeep linear networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Factorization of matrices (15A23)

Related Items (5)

Efficient Identification of Butterfly Sparse Matrix Factorizations ⋮ A survey on deep matrix factorizations ⋮ Spherical Image Inpainting with Frame Transformation and Data-Driven Prior Deep Networks ⋮ Parameter identifiability of a deep feedforward ReLU neural network ⋮ An embedding of ReLU networks and an analysis of their identifiability

Uses Software

• PhaseLift

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Witness sets of projections
• On the identifiability of overcomplete dictionaries via the minimisation principle underlying K-SVD
• Toward fast transform learning
• Nonparametric regression using deep neural networks with ReLU activation function
• Rapid, robust, and reliable blind deconvolution via nonconvex optimization
• Membership tests for images of algebraic sets by linear projections
• Exact matrix completion via convex optimization
• PhaseLift: Exact and Stable Signal Recovery from Magnitude Measurements via Convex Programming
• Sparse Signal Recovery from Quadratic Measurements via Convex Programming
• Sparse and Spurious: Dictionary Learning With Noise and Outliers
• Sample Complexity of Dictionary Learning and Other Matrix Factorizations
• A Clustering Approach to Learning Sparsely Used Overcomplete Dictionaries
• Fundamental Performance Limits for Ideal Decoders in High-Dimensional Linear Inverse Problems
• Blind Deconvolution Using Convex Programming
• Compressed sensing and best 𝑘-term approximation
• Lifting for Blind Deconvolution in Random Mask Imaging: Identifiability and Convex Relaxation
• Self-calibration and biconvex compressive sensing
• Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
• On the Complexity of Nonnegative Matrix Factorization
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• Universal approximation bounds for superpositions of a sigmoidal function
• On Convergence of Kronecker Graphical Lasso Algorithms
• Spurious Valleys in Two-layer Neural Network Optimization Landscapes
• Dictionary Identification—Sparse Matrix-Factorization via $\ell_1$-Minimization
• The Power of Convex Relaxation: Near-Optimal Matrix Completion
• Basic Algebraic Geometry 1
• Learning the parts of objects by non-negative matrix factorization
• Computing a nonnegative matrix factorization -- provably
• The Rotation of Eigenvectors by a Perturbation. III
• Phase Retrieval via Matrix Completion
• Compressed sensing

This page was built for publication: Multilinear Compressive Sensing and an Application to Convolutional Linear Networks