Stability of randomized learning algorithms

MaRDI QIDQ3093240zbMATH OpenFDO

Authors André Elisseeff, Theodoros Evgeniou, Massimiliano Pontil

Publication date 12 October 2011

Full work available at URL http://www.jmlr.org/papers/v6/elisseeff05a.html

zbMATH Keywords

sensitivity analysisstabilitygeneralization errorbaggingbootstrap methodsrandomized learning algorithmsleave-one-out error

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Randomized algorithms (68W20)

Recommendations

• STABILITY RESULTS IN LEARNING THEORY
• 10.1162/153244302760200704
• scientific article; zbMATH DE number 6001978
• Leave one out error, stability, and generalization of voting combinations of classifiers
• Estimating a sharp convergence bound for randomized ensembles

Cited in

(30)

• Efficient and reliable overlay networks for decentralized federated learning
• Bootstrap SGD: algorithmic stability and robustness
• Learning with mitigating random consistency from the accuracy measure
• A tighter generalization error bound for wide GCN based on loss landscape
• Stability of unstable learning algorithms
• Optimization and learning with randomly compressed gradient updates
• Tikhonov, Ivanov and Morozov regularization for support vector machine learning
• Supervised Learning by Support Vector Machines
• Understanding generalization error of SGD in nonconvex optimization
• Estimating a sharp convergence bound for randomized ensembles
• Efficient cross-validation for kernelized least-squares regression with sparse basis expansions
• scientific article; zbMATH DE number 702045 (Why is no real title available?)
• Algorithmic stability of heavy-tailed stochastic gradient descent on least squares
• Random projection preserves stability with high probability
• An exponential Efron-Stein inequality for L_q stable learning rules
• Consolidated trees versus bagging when explanation is required
• Incremental update of approximations in dominance-based rough sets approach under the variation of attribute values
• Stability and optimization error of stochastic gradient descent for pairwise learning
• Stability and Convergence of Principal Component Learning Algorithms
• Stability of Neural Networks for Slightly Perturbed Training Data Sets
• The limits of assumption-free tests for algorithm performance
• Stability behavior for unsupervised learning
• Approximation stability and boosting
• scientific article; zbMATH DE number 6001978 (Why is no real title available?)
• Stability analysis of stochastic gradient descent for homogeneous neural networks and linear classifiers
• Algorithmic stability implies training-conditional coverage for distribution-free prediction methods
• The generalization error bound for a stochastic gradient descent family via a Gaussian approximation method
• scientific article; zbMATH DE number 2217750 (Why is no real title available?)
• High-probability generalization bounds for pointwise uniformly stable algorithms
• Editorial: Randomized algorithms for training neural networks

This page was built for publication: Stability of randomized learning algorithms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3093240)