Noisy classification with boundary assumptions

Abstract

We address the problem of classification when data are collected from two samples with measurement errors. This problem turns to be an inverse problem and requires a specific treatment. In this context, we investigate the minimax rates of convergence using both a margin assumption, and a smoothness condition on the boundary of the set associated to the Bayes classifier. We establish lower and upper bounds (based on a deconvolution classifier) on these rates.

arXiv admin note: substantial text overlap with arXiv:1201.3283

References in corpus (7)

• Fast learning rates for plug-in classifiers
• Risk bounds for statistical learning
• On deconvolution with repeated measurements
• Goodness-of-fit testing and quadratic functional estimation from indirect observations
• Minimax fast rates for discriminant analysis with errors in variables
• Empirical risk minimization in inverse problems
• Anisotropic oracle inequalities in noisy quantization