Universal Consistency and Robustness of Localized Support Vector Machines
The massive amount of available data potentially used to discover patters in machine learning is a challenge for kernel based algorithms with respect to runtime and storage capacities. Local approaches might help to relieve these issues. From a statistical point of view local approaches allow additionally to deal with different structures in the data in different ways. This paper analyses properties of localized kernel based, non-parametric statistical machine learning methods, in particular of support vector machines (SVMs) and methods close to them. We will show there that locally learnt kernel methods are universal consistent. Furthermore, we give an upper bound for the maxbias in order to show statistical robustness of the proposed method.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningSimilar Papers 제목 키워드 기반
Universal Consistency of Multi-Class Support Vector Classification
Steinwart was the first to prove universal consistency of support vector machine classification. His proof analyzed the ‘standard’ support vector machine classifier, which is restricted to binary classification problems. I…
ClassificationGeneral ClassificationLp- and Risk Consistency of Localized SVMs
Kernel-based regularized risk minimizers, also called support vector machines (SVMs), are known to possess many desirable properties but suffer from their super-linear computational requirements when dealing with large d…
Evaluating Adversarial Robustness of Low dose CT Recovery
Low dose computed tomography (CT) acquisition using reduced radiation or sparse angle measurements is recommended to decrease the harmful effects of X-ray radiation. Recent works successfully apply deep networks to the p…
Adversarial RobustnessComputed Tomography (CT)Data-driven intrinsic localized mode detection and classification in one-dimensional crystal lattice model
In this work we propose Support Vector Machine classification algorithms to classify onedimensional crystal lattice waves from locally sampled data. Different learning datasets of particle displacements, momenta and ener…
ClassificationDimensionality ReductionUniversality of high-dimensional scaling limits of stochastic gradient descent
We consider statistical tasks in high dimensions whose loss depends on the data only through its projection into a fixed-dimensional subspace spanned by the parameter vectors and certain ground truth vectors. This includ…