Optimal Learning from the Doob-Dynkin lemma

MaRDI QIDQ6295975zbMATH OpenFDO

Authors Gunnar Taraldsen

Publication date 3 January 2018

Abstract: The Doob-Dynkin Lemma gives conditions on two functions $X$ and $Y$ that ensure existence of a function $phi$ so that $X=phicircY$. This communication proves different versions of the Doob-Dynkin Lemma, and shows how it is related to optimal statistical learning algorithms. Keywords and phrases: Improper prior, Descriptive set theory, Conditional Monte Carlo, Fiducial, Machine learning, Complex data.

This page was built for publication: Optimal Learning from the Doob-Dynkin lemma

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6295975)