A unifying representer theorem for inverse problems and machine learning

DOI10.1007/S10208-020-09472-XzbMath1479.46088arXiv1903.00687OpenAlexW3088481514WikidataQ130240264 ScholiaQ130240264MaRDI QIDQ2231644

Michael Unser

Publication date: 30 September 2021

Published in: Foundations of Computational Mathematics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1903.00687

zbMATH Keywords

convex optimizationinverse problemregularizationBanach spacemachine learningrepresenter theorem

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Applications of functional analysis in optimization, convex analysis, mathematical programming, economics (46N10) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20) Linear operators and ill-posed problems, regularization (47A52)

Related Items (23)

A superposition principle for the inhomogeneous continuity equation with Hellinger–Kantorovich-regular coefficients ⋮ Neural network approximation ⋮ Two-Layer Neural Networks with Values in a Banach Space ⋮ Parameter choices for sparse regularization with the ℓ1 norm ^* ⋮ What Kinds of Functions Do Deep Neural Networks Learn? Insights from Variational Spline Theory ⋮ Explicit representations for Banach subspaces of Lizorkin distributions ⋮ A generalized conditional gradient method for dynamic inverse problems with optimal transport regularization ⋮ Sparse machine learning in Banach spaces ⋮ Linear inverse problems with Hessian-Schatten total variation ⋮ Optimal learning ⋮ A duality approach to regularized learning problems in Banach spaces ⋮ The Geometry of Sparse Analysis Regularization ⋮ Regularization method for the generalized moment problem in a functional reproducing kernel Hilbert space ⋮ Functions with bounded Hessian-Schatten variation: density, variational, and extremality properties ⋮ On the determination of Lagrange multipliers for a weighted Lasso problem using geometric and convex analysis techniques ⋮ Weighted variation spaces and approximation by shallow ReLU networks ⋮ Unnamed Item ⋮ Distributional extension and invertibility of the \(k\)-plane transform and its dual ⋮ Splitting method for support vector machine in reproducing kernel Banach space with a lower semi-continuous loss function ⋮ From kernel methods to neural networks: a unifying variational formulation ⋮ Functional estimation of anisotropic covariance and autocovariance operators on the sphere ⋮ Minimum norm interpolation in the ℓ1(ℕ) space ⋮ On the extremal points of the ball of the Benamou–Brenier energy

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A mathematical introduction to compressive sensing
• Regularization methods in Banach spaces.
• Super-resolution from noisy data
• Support recovery for sparse super-resolution of positive measures
• Regularized learning in Banach spaces as an optimization problem: representer theorems
• Irrotational or divergence-free interpolation
• A theorem on duality mappings in Banach spaces
• Exact support recovery for sparse spikes deconvolution
• Kernel methods in machine learning
• Kernels, regularization and differential equations
• Spline solutions to L\(^1\) extremal problems in one and several variables
• On 'best' interpolation
• Vector-valued reproducing kernel Banach spaces with applications to multi-task learning
• Regularization networks and support vector machines
• Sparsity of solutions for variational inverse problems with finite-dimensional data
• Some results on Tchebycheffian spline functions and stochastic processes
• Kernels for Vector-Valued Functions: A Review
• Representer Theorems for Sparsity-Promoting <inline-formula> <tex-math notation="LaTeX">$\ell _{1}$ </tex-math> </inline-formula> Regularization
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• Regularization theory in image restoration-the stabilizing functional approach
• Semi-reproducing kernel Hilbert spaces, splines and increment kriging
• From Sparse Solutions of Systems of Equations to Sparse Modeling of Signals and Images
• An Introduction to Banach Space Theory
• Splines Are Universal Solutions of Linear Inverse Problems with Generalized TV Regularization
• Regularized learning schemes in feature Banach spaces
• Super-resolution of point sources via convex programming
• Continuous-Domain Solutions of Linear Inverse Problems With Tikhonov Versus Generalized TV Regularization
• MultiDimensional Sparse Super-Resolution
• Inverse problems in spaces of measures
• On Representer Theorems and Convex Regularization
• Sparsity and incoherence in compressive sampling
• A representer theorem for deep kernel learning
• Generalized Mercer Kernels and Reproducing Kernel Banach Spaces
• Towards a Mathematical Theory of Super‐resolution
• On Learning Vector-Valued Functions
• Theory of Reproducing Kernels
• Compressed sensing

This page was built for publication: A unifying representer theorem for inverse problems and machine learning