On the Consistency of the Bootstrap Approach for Support Vector Machines and Related Kernel Based Methods

It is shown that bootstrap approximations of support vector machines (SVMs) based on a general convex and smooth loss function and on a general kernel are consistent. This result is useful for approximating the unknown finite sample distribution of SVMs by the bootstrap approach.

stat.ML cs.LG Computer Science Mathematics

View graph Source

Paper

References (21)

01Statistical Learning TheoryYuhai Wu2021 · Technometrics · 22k citations

02An Introduction to Nonlinear Analysis: TheoryZ. Denkowski, Stanislaw Migrski, Nikolaos S. Papageorgiou2013 · 501 citations

03Asymptotic normality of support vector machine variants and other regularized kernel methodsR. Hable2010 · Journal of Multivariate Analysis · 52 citations In Library

04Support vector machinesIngo Steinwart, A. Christmann2008 · Data Mining and Knowledge Discovery Handbook · 8.5k citations

05Learning Theory: An Approximation Theory Viewpoint: IndexF. Cucker, Ding-Xuan Zhou2007 · 453 citations

06Learning Theory Estimates via Integral Operators and Their ApproximationsS. Smale, Ding-Xuan Zhou2007 · 689 citations

07An introduction to nonlinear analysisZ. Denkowski, S. Migórski, N. Papageorgiou2003 · 390 citations

08Learning with Kernels: support vector machines, regularization, optimization, and beyondB. Scholkopf, Alex Smola2001 · Adaptive computation and machine learning series · 5.4k citations

09Learning with kernels2001

10Learning With Kernels: Support Vector Machines, Regularization, Optimization, and BeyondChristopher K. I. Williams2001 · 1.5k citations

11Devroye, L., Gyorfi, L. and Lugosi, G. : A Probabilistic Theory of Pattern Recognition, Springer (1996).中澤真1997 · 350 citations

12Weak Convergence and Empirical Processes: With Applications to StatisticsT. Mikosch, A. Vaart, J. Wellner1996 · 6.6k citations

Scroll for more · 9 remaining

Similar papers

Support Vector Machines for Additive Models: Consistency and RobustnessA. Christmann, R. Hable2010 · arXiv: Machine Learning · 2 citations In Library

Universal Consistency and Robustness of Localized Support Vector MachinesFlorian Dumpert, A. Christmann2017 · Neurocomputing · 18 citations In Library

On the Consistency of Kernel Methods with Dependent ObservationsP. Massiani, Sebastian Trimpe, Friedrich Solowjow2024 · International Conference on Machine Learning · 3 citations In Library

Consistency of the bootstrap for asymptotically linear estimators based on machine learningZhou Tang, T. Westling2024 · 6 citations In Library

Randomized Kernel Methods for Least-Squares Support Vector MachinesM. Andrecut2017 · arXiv.org · 5 citations In Library

Quantitative Robustness of Localized Support Vector MachinesFlorian Dumpert2019 · Communications on Pure and Applied Analysis · 5 citations In Library

Quantitative robustness of localized support vector machinesFlorian Dumpert2020 · Communications on Pure &amp Applied Analysis In Library

Validate Model Endorsed for Support Vector Machine Alignment with Kernel Function and Depth Concept to Get Superlative AccuratenessDr. R. Muthukrishnan, N. Prakash2023 · International Journal of Basic Sciences and Applied Computing · 0 citations In Library

Convex Loss Functions for Support Vector Machines (SVMs) and Neural NetworksFilippo Portera2026 In Library

Convex Loss Functions for Support Vector Machines (SVMs) and Neural NetworksF. Portera2026 · 0 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal