A Generalization of the Glivenko-Cantelli Theorem

By H. Tucker. 1959

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Deep Learning Scaling is Predictable, Empirically (2017, background): “This proof inspects the asymptotic rate of convergence of the Glivenko-Cantelli theorem limit (Tucker (1959)).”
Endogenous post-stratification in surveys: Classifying with a sample-fitted model (2008, background): “The uniform convergence in D1 is met by independent and identically distributed sequences (Glivenko–Cantelli lemma), stationary ergodic sequences (Tucker [13]), certain deterministic sequences [e.”
Monte Carlo Maximum Likelihood Estimation for Discretely Observed Diffusion Processes (2009, background): “, [11, 38, 39] for the Glivenko–Cantelli problem and [13, 40] for the consistency of the maximum likelihood estimator), dynamical systems and ergodic theory, stochastic optimization, econometrics [2] and Monte Carlo methods [22]; see Chapter 1 of [33] for a review.”
On the Benjamini-Hochberg method (2006, result): “2) hold true uniformly in x; a similar result (with a stronger conclusion) for stationary ergodic sequences has been given by Tucker [21], for example.”