Balancing principle in supervised learning for a general regularization scheme
Authors:
- Shuai LuSLShuai Lu
- Peter MathéPMPeter Mathé
- Sergei V. PereverzevSPSergei V. Pereverzev
- 1 January 2020
- journal article
- research article
- Published by Elsevier in Applied and Computational Harmonic Analysis
- Vol. 48 (1) , 123-148
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (11522108, 91730304)
- Special Funds for Major State Basic Research Projects of China (2015CB856003)
- Shanghai Municipal Education Commission (16SG01)
- Austrian Science Fund (I1669)
- EU-Horizin 2020 MSC-RISE (AMMODIT)
This publication has 18 references indexed in Scilit:
- Learning theory of distributed spectral algorithmsInverse Problems, 2017
- Oracle-type posterior contraction rates in Bayesian inverse problemsInverse Problems and Imaging, 2015
- Radial kernels and their reproducing kernel Hilbert spacesJournal of Complexity, 2010
- CROSS-VALIDATION BASED ADAPTATION FOR REGULARIZATION OPERATORS IN LEARNING THEORYAnalysis and Applications, 2010
- Adaptive Kernel Methods Using the Balancing PrincipleFoundations of Computational Mathematics, 2010
- On Early Stopping in Gradient Descent LearningConstructive Approximation, 2007
- Learning Theory Estimates via Integral Operators and Their ApproximationsConstructive Approximation, 2007
- On regularization algorithms in learning theoryJournal of Complexity, 2007
- Optimal Rates for the Regularized Least-Squares AlgorithmFoundations of Computational Mathematics, 2006
- Regularization Networks and Support Vector MachinesAdvances in Computational Mathematics, 2000