Learning from dependent observations

Authors:
Ingo Steinwart;Don Hush;Clint Scovel
Affiliations:
Information Sciences Group, CCS-3 MS B256, Los Alamos National Laboratory, Los Alamos, NM 87545, USA;Information Sciences Group, CCS-3 MS B256, Los Alamos National Laboratory, Los Alamos, NM 87545, USA;Information Sciences Group, CCS-3 MS B256, Los Alamos National Laboratory, Los Alamos, NM 87545, USA
Venue:
Journal of Multivariate Analysis
Year:
2009

Citing 12
Cited 7

On consistency in nonparametric estimation under mixing conditions

Journal of Multivariate Analysis
Nonparametric Time Series Prediction Through Adaptive ModelSelection

Machine Learning
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
A Theory of Learning and Generalization: With Applications to Neural Networks and Control Systems

A Theory of Learning and Generalization: With Applications to Neural Networks and Control Systems
Support vector machines are universally consistent

Journal of Complexity
On the influence of the kernel on the consistency of support vector machines

The Journal of Machine Learning Research
Support Vector Machine Soft Margin Classifiers: Error Analysis

The Journal of Machine Learning Research
Some Properties of Regularized Kernel Methods

The Journal of Machine Learning Research
Fast rates for support vector machines

COLT'05 Proceedings of the 18th annual conference on Learning Theory
Exponential convergence rates in classification

COLT'05 Proceedings of the 18th annual conference on Learning Theory
Memory-universal prediction of stationary random processes

IEEE Transactions on Information Theory
Consistency of support vector machines and other regularized kernel classifiers

IEEE Transactions on Information Theory

Learning from uniformly ergodic Markov chains

Journal of Complexity
Online Learning with Samples Drawn from Non-identical Distributions

The Journal of Machine Learning Research
Generalization bounds of ERM algorithm with V-geometrically Ergodic Markov chains

Advances in Computational Mathematics
Classification with non-i.i.d. sampling

Mathematical and Computer Modelling: An International Journal
Security analysis of online centroid anomaly detection

The Journal of Machine Learning Research
Consistent identification of Wiener systems: A machine learning viewpoint

Automatica (Journal of IFAC)
Compressed classification learning with Markov chain samples

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In most papers establishing consistency for learning algorithms it is assumed that the observations used for training are realizations of an i.i.d. process. In this paper we go far beyond this classical framework by showing that support vector machines (SVMs) only require that the data-generating process satisfies a certain law of large numbers. We then consider the learnability of SVMs for @a-mixing (not necessarily stationary) processes for both classification and regression, where for the latter we explicitly allow unbounded noise.