Learning from dependent observations

2007/07/02 by Ingo Steinwart, Steinwart, Ingo, Don Hush +3 · 1 citation
Computer Science · Engineering · Mathematics · #Control Systems and Identification #FOS: Computer and information sciences #Machine Learning (stat.ML) #Machine Learning and Algorithms #Methodology (stat.ME) #Statistical Methods and Inference #stat.ME #stat.ML

paper · pdf · doi:10.48550/arxiv.0707.0303

submitted to Journal of Multivariate Analysis

arxiv created 2007/07/02 · openalex publication_date 2007/07/02 · arxiv updated 2009/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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) essentially 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.

Cited by

• Rademacher learning rates for iterated random functions

Related

• Learning theory estimates with observations from general stationary stochastic processes
• On the Consistency of Kernel Methods with Dependent Observations
• Practical machine learning is learning on small samples
• Stability Bound for Stationary Phi-mixing and Beta-mixing Processes
• Learning properties of Support Vector Machines