Plug-in Estimators for Conditional Expectations and Probabilities

Grunewalder, Steffen (2018) Plug-in Estimators for Conditional Expectations and Probabilities. In: Proceedings of the 21st International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research . PMLR, ESP, pp. 1513-1521.

[thumbnail of grunewalder18]
Preview
PDF (grunewalder18)
grunewalder18.pdf - Accepted Version

Download (253kB)

Abstract

We study plug-in estimators of conditional expectations and probabilities, and we provide a systematic analysis of their rates of convergence. The plug-in approach is particularly useful in this setting since it introduces a natural link to VC- and empirical process theory. We make use of this link to derive rates of convergence that hold uniformly over large classes of functions and sets, and under various conditions. For instance, we demonstrate that elementary conditional probabilities are estimated by these plug-in estimators with a rate of n˛1=2 if one conditions with a VC-class of sets and where ˛ 2 Œ0; 1=2/ controls a lower bound on the size of sets we can estimate given n samples. We gain similar results for Kolmogorov’s conditional expectation and probability which generalize the elementary forms of conditioning. Due to their simplicity, plug-in estimators can be evaluated in linear time and there is no up-front cost for inference

Item Type:
Contribution in Book/Report/Proceedings
Additional Information:
Proceedings of the 21st International Conference on Artificial Intelligence and Statistics (AISTATS) 2018, Lanzarote, Spain. PMLR: Volume 84. Copyright 2018 by the author(s).
ID Code:
124325
Deposited By:
Deposited On:
03 Apr 2018 10:02
Refereed?:
Yes
Published?:
Published
Last Modified:
17 Sep 2023 04:01