The Grothendieck duality and sparse minimizing in spaces of Sobolev solutions to elliptic systems
Preprint
Abstract
We present an instructive example of using Banach spaces of solutions to (linear, generally, non-scalar) elliptic operator $A$ to investigate variational inverse problems related to neural networks and/or to regularization of solutions to boundary value problems. More precisely, inspired by kernel's method for optimization problems in locally convex spaces, we prove the existence of the so-called sparse minimizers for the related variational problem and produce a representer theorem where a suitable fundamental solution of the operator $A$ is used as a reproducing kernel. The Grothendieck type duality for the Sobolev spaces of solutions to elliptic operator $A$ plays an essential role in the considerations. The case where the number of data passes to infinity is also discussed. Some typical situations related to the standard elliptic operators, the corresponding function spaces and fundamental solutions are considered.
Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- From Kernel Methods to Neural Networks: A Unifying Variational FormulationFoundations of Computational Mathematics, 2023
- On Reproducing Kernel Banach Spaces: Generic Definitions and Unified Framework of ConstructionsActa Mathematica Sinica, English Series, 2022
- What Kinds of Functions Do Deep Neural Networks Learn? Insights from Variational Spline TheorySIAM Journal on Mathematics of Data Science, 2022
- A Unifying Representer Theorem for Inverse Problems and Machine LearningFoundations of Computational Mathematics, 2020
- VECTOR VALUED REPRODUCING KERNEL HILBERT SPACES AND UNIVERSALITYAnalysis and Applications, 2010
- Reproducing kernel Banach spaces for machine learning2009
- Convex Analysis and Variational Problems1999
- On Iterations of the Green Integrals and their Applications to Elliptic Differential ComplexesMathematische Nachrichten, 1996
- Bases With Double Orthogonality in the Cauchy Problem for Systems With Injective SymbolsProceedings of the London Mathematical Society, 1995
- Ill-Posed Problems of Mathematical Physics and Analysis1986