Electronic Journal of Statistics · 2013 · 12 citations · 21 references
ComputingMathematicsMachine LearningProbability TheoryStatistical LearningBayesian InferenceDensity EstimationLoss FunctionProbabilistic Machine LearningStatistical InferenceBayesian Inverse ProblemsEmpirical Bayes Risk EstimationEmpirical Risk ManagementExcess Risk ModelStatistical Learning Theory
Let $(X,Y)\in\mathcal{X}\times\mathcal{Y}$ be a random couple with unknown distribution $P$. Let $\mathcal{G}$ be a class of measurable functions and $\ell$ a loss function. The problem of statistical learning deals with the estimation of the Bayes: \[g^{*}=\arg\min_{g\in\mathcal{G}}\mathbb{E}_{P}\ell(g,(X,Y)).\] In this paper, we study this problem when we deal with a contaminated sample $(Z_{1},Y_{1}),\dots,(Z_{n},Y_{n})$ of i.i.d. indirect observations. Each input $Z_{i}$, $i=1,\dots,n$ is distributed from a density $Af$, where $A$ is a known compact linear operator and $f$ is the density of the direct input $X$. We derive fast rates of convergence for the excess risk of empirical risk minimizers based on regularization methods, such as deconvolution kernel density estimators or spectral cut-off. These results are comparable to the existing fast rates in Koltchinskii (2006) for the direct case. It gives some insights into the effect of indirect measurements in the presence of fast rates of convergence.
21
Optimal aggregation of classifiers in statistical learning
A. B. Tsybakov · The Annals of Statistics · 2004 · 601 citations · Full text
New concentration inequalities in product spaces
Michel Talagrand · Inventiones mathematicae · 1996 · 526 citations
Smooth discrimination analysis
Enno Mammen, Alexandre B. Tsybakov · The Annals of Statistics · 1999 · 403 citations · Full text