Local Moment Matching: A Unified Methodology for Symmetric Functional Estimation and Distribution Estimation Under Wasserstein Distance
Abstract
We present \emph{Local Moment Matching (LMM)}, a unified methodology for symmetric functional estimation and distribution estimation under Wasserstein distance. We construct an efficiently computable estimator that achieves the minimax rates in estimating the distribution up to permutation, and show that the plug-in approach of our unlabeled distribution estimator is "universal" in estimating symmetric functionals of discrete distributions. Instead of doing best polynomial approximation explicitly as in existing literature of functional estimation, the plug-in approach conducts polynomial approximation implicitly and attains the optimal sample complexity for the entropy, power sum and support size functionals.
Cite
Text
Han et al. "Local Moment Matching: A Unified Methodology for Symmetric Functional Estimation and Distribution Estimation Under Wasserstein Distance." Annual Conference on Computational Learning Theory, 2018.Markdown
[Han et al. "Local Moment Matching: A Unified Methodology for Symmetric Functional Estimation and Distribution Estimation Under Wasserstein Distance." Annual Conference on Computational Learning Theory, 2018.](https://mlanthology.org/colt/2018/han2018colt-local/)BibTeX
@inproceedings{han2018colt-local,
title = {{Local Moment Matching: A Unified Methodology for Symmetric Functional Estimation and Distribution Estimation Under Wasserstein Distance}},
author = {Han, Yanjun and Jiao, Jiantao and Weissman, Tsachy},
booktitle = {Annual Conference on Computational Learning Theory},
year = {2018},
pages = {3189-3221},
url = {https://mlanthology.org/colt/2018/han2018colt-local/}
}