paper

Contraction and uniform convergence of isotonic regression

arXiv:1706.01852

Abstract

We consider the problem of isotonic regression, where the underlying signal is assumed to satisfy a monotonicity constraint, that is, lies in the cone . We study the isotonic projection operator (projection to this cone), and find a necessary and sufficient condition characterizing all norms with respect to which this projection is contractive. This enables a simple and non-asymptotic analysis of the convergence properties of isotonic regression, yielding uniform confidence bands that adapt to the local Lipschitz properties of the signal.

References in corpus (1)

Cited by in corpus (2)