Generalization bounds of regularization algorithms derived simultaneously through hypothesis space complexity, algorithmic stability and data quality
From MaRDI portal
Publication:3087503
Recommendations
- 10.1162/153244302760200704
- Learning with generalization capability by kernel methods of bounded complexity
- scientific article; zbMATH DE number 6001978
- Stability and generalization of learning algorithm: a new framework of stability
- Generalization bounds of a compressed regression learning algorithm
Cites work
- scientific article; zbMATH DE number 1332320 (Why is no real title available?)
- Best choices for regularization parameters in learning theory: on the bias-variance problem.
- Capacity of reproducing kernel spaces in learning theory
- Learning Theory
- Learning from dependent observations
- Learning rates of least-square regularized regression
- On the mathematical foundations of learning
- Regularization networks and support vector machines
- SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming
- Shannon sampling and function reconstruction from point values
- The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
Cited in
(10)- Concentration estimates for learning with \(\ell ^{1}\)-regularizer and data dependent hypothesis spaces
- Attribute reduction of concept lattice based on irreducible elements
- Elastic-net regularization for low-rank matrix recovery
- Learning performance of Tikhonov regularization algorithm with geometrically beta-mixing observations
- Regularized least square algorithm with two kernels
- Block-regularized repeated learning-testing for estimating generalization error
- Stability and generalization of learning algorithm: a new framework of stability
- scientific article; zbMATH DE number 5957262 (Why is no real title available?)
- 10.1162/153244302760200704
- Learning rates for the kernel regularized regression with a differentiable strongly convex loss
This page was built for publication: Generalization bounds of regularization algorithms derived simultaneously through hypothesis space complexity, algorithmic stability and data quality
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3087503)
