Inverse problems are solvable on real number signal processing hardware

DOI10.1016/J.ACHA.2024.101719MaRDI QIDQ6652581zbMATH OpenFDO

Authors Holger Boche, Adalbert Fono, Gitta Kutyniok

Publication date 12 December 2024

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

Full work available at URL https://doi.org/10.1016/J.ACHA.2024.101719

zbMATH Keywords

deep learninginverse problemsBSS machinescomputing theory

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Signal theory (characterization, reconstruction, filtering, etc.) (94A12) General topics in the theory of computing (68Q01)

Recommendations

• Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems
• Deep learning for trivial inverse problems
• DRIP: deep regularizers for inverse problems
• Deep learning for inverse problems. Abstracts from the workshop held March 7--13, 2021 (hybrid meeting)

Cites work

• scientific article; zbMATH DE number 52121 (Why is no real title available?)
• scientific article; zbMATH DE number 1201576 (Why is no real title available?)
• scientific article; zbMATH DE number 1460545 (Why is no real title available?)
• scientific article; zbMATH DE number 2115098 (Why is no real title available?)
• scientific article; zbMATH DE number 3336816 (Why is no real title available?)
• scientific article; zbMATH DE number 3068536 (Why is no real title available?)
• A new decision method for elementary algebra
• A note of computation for M-P inverse \(A^{\dagger }\)
• AMP-Inspired Deep Networks for Sparse Linear Inverse Problems
• Algorithms and Computation
• Algorithms in real algebraic geometry
• An iterative thresholding algorithm for linear inverse problems with a sparsity constraint
• Atomic Decomposition by Basis Pursuit
• Bayesian Compressive Sensing
• Compressed sensing
• Decoding by Linear Programming
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Deep learning
• Denial-of-Service Attacks on Communication Systems: Detectability and Jammer Knowledge
• Just relax: convex programming methods for identifying sparse signals in noise
• Le calcul des intégrales définies.
• Learning representations by back-propagating errors
• Learning the invisible: a hybrid deep learning-shearlet framework for limited angle computed tomography
• Limitations of deep learning for inverse problems on digital hardware
• Mathematical problems. Lecture delivered before the international congress of mathematicians at Paris in 1900. Translated by \textit{Mary Winston Newson}.
• Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
• On Computable Numbers, with an Application to the Entscheidungsproblem
• On a theory of computation and complexity over the real numbers: 𝑁𝑃- completeness, recursive functions and universal machines
• On the Perturbation of Pseudo-Inverses, Projections and Linear Least Squares Problems
• Optimized Projections for Compressed Sensing
• Recent advances in the computation of the homology of semialgebraic sets
• Recursively enumerable sets and degrees
• Reluplex: an efficient SMT solver for verifying deep neural networks
• Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information
• Solving ill-posed inverse problems using iterative deep neural networks
• Solving inverse problems using data-driven models
• Sparse Reconstruction by Separable Approximation
• Sparse Regularization via Convex Analysis
• Sparse solutions to linear inverse problems with multiple measurement vectors
• Square-root lasso: pivotal recovery of sparse signals via conic programming
• Stable signal recovery from incomplete and inaccurate measurements
• Structured Compressed Sensing: From Theory to Applications
• The Group Lasso for Stable Recovery of Block-Sparse Signal Representations
• Turing's legacy. Developments from Turing's ideas in logic

Cited in

(2)

• Mathematical algorithm design for deep learning under societal and judicial constraints: the algorithmic transparency requirement
• Computability of classification and deep learning: from theoretical limits to practical feasibility through quantization

This page was built for publication: Inverse problems are solvable on real number signal processing hardware

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6652581)