A machine learning approach to optimal Tikhonov regularization I: Affine manifolds
DOI10.1142/S0219530520500220zbMath1493.62438arXiv1610.01952OpenAlexW3117295477MaRDI QIDQ5077184
Massimo Fornasier, Ernesto De Vito, Valeriya Naumova
Publication date: 18 May 2022
Published in: Analysis and Applications (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1610.01952
Tikhonov regularizationconcentration inequalitieshigh-dimensional function approximationparameter choice rulesub-Gaussian vectors
Nonparametric regression and quantile regression (62G08) Ridge regression; shrinkage estimators (Lasso) (62J07) Linear operators and ill-posed problems, regularization (47A52)
Related Items (1)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions
- Multi-scale geometric methods for data sets. II: Geometric multi-resolution analysis
- Comparing parameter choice methods for regularization of ill-posed problems
- Shearlets. Multiscale analysis for multivariate data.
- Hanson-Wright inequality and sub-Gaussian concentration
- Optimal order of convergence and (in)tractability of multivariate approximation of smooth functions
- A meta-learning approach to the regularized learning -- case study: blood glucose prediction
- Adaptive kernel methods using the balancing principle
- Regularization by architecture: a deep prior approach for inverse problems
- Balancing principle in supervised learning for a general regularization scheme
- Multiscale geometric methods for data sets. I: Multiscale SVD, noise and curvature.
- Convergence analysis of minimization-based noise level-free parameter choice rules for linear ill-posed problems
- The Optimal Hard Threshold for Singular Values is <inline-formula> <tex-math notation="TeX">\(4/\sqrt {3}\) </tex-math></inline-formula>
- Deep Learning for Trivial Inverse Problems
- Some considerations concerning regularization and parameter choice algorithms
- Generalized Cross-Validation as a Method for Choosing a Good Ridge Parameter
- Data driven regularization by projection
- Multi-Resolution Geometric Analysis for Data in High Dimensions
This page was built for publication: A machine learning approach to optimal Tikhonov regularization I: Affine manifolds
