Measuring Complexity of Learning Schemes Using Hessian-Schatten Total Variation

DOI10.1137/22m147517xarXiv2112.06209OpenAlexW4379232433MaRDI QIDQ6171683

Shayan Aziznejad, Joaquim Campos, Michael Unser

Publication date: 14 August 2023

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

Full work available at URL: https://arxiv.org/abs/2112.06209

zbMATH Keywords

total variationsupervised learningSchatten normHessian operatorcontinuous and piecewise-linear functions

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) Absolutely continuous real functions of several variables, functions of bounded variation (26B30) Spaces of measures (46E27)

Related Items (2)

Linear inverse problems with Hessian-Schatten total variation ⋮ Functions with bounded Hessian-Schatten variation: density, variational, and extremality properties

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Regularization of linear inverse problems with total generalized variation
• Fonctions à hessien borné
• A second-order model for image denoising
• Networks and the best approximation property
• Théorie des distributions à valeurs vectorielles
• Variational methods on the space of functions of bounded Hessian for convexification and denoising
• Regularization in kernel learning
• Riesz potentials, higher Riesz transforms and Beppo Levi spaces
• A distribution-free theory of nonparametric regression
• Regularization networks and support vector machines
• Sparsest piecewise-linear regression of one-dimensional data
• Optimal rates for the regularized least-squares algorithm
• Impulse functions over curves and surfaces and their applications to diffraction
• Some results on Tchebycheffian spline functions and stochastic processes
• Convex optimization in sums of Banach spaces
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• An Introduction to Sparse Stochastic Processes
• Support Vector Machines
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Duality Mapping for Schatten Matrix Norms
• What Kinds of Functions Do Deep Neural Networks Learn? Insights from Variational Spline Theory
• Benign overfitting in linear regression
• Higher-order total variation approaches and generalisations
• Structure Tensor Total Variation
• Hessian-Based Norm Regularization for Image Restoration With Biomedical Applications
• Hessian Schatten-Norm Regularization for Linear Inverse Problems
• Total Generalized Variation
• Deep learning: a statistical viewpoint
• Compressed sensing
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Measuring Complexity of Learning Schemes Using Hessian-Schatten Total Variation