Nonparametric Density Estimation Under Distribution Drift
Abstract
We study nonparametric density estimation in non-stationary drift settings. Given a sequence of independent samples taken from a distribution that gradually changes in time, the goal is to compute the best estimate for the current distribution. We prove tight minimax risk bounds for both discrete and continuous smooth densities, where the minimum is over all possible estimates and the maximum is over all possible distributions that satisfy the drift constraints. Our technique handles a broad class of drift models and generalizes previous results on agnostic learning under drift.
Cite
Text
Mazzetto and Upfal. "Nonparametric Density Estimation Under Distribution Drift." International Conference on Machine Learning, 2023.Markdown
[Mazzetto and Upfal. "Nonparametric Density Estimation Under Distribution Drift." International Conference on Machine Learning, 2023.](https://mlanthology.org/icml/2023/mazzetto2023icml-nonparametric/)BibTeX
@inproceedings{mazzetto2023icml-nonparametric,
title = {{Nonparametric Density Estimation Under Distribution Drift}},
author = {Mazzetto, Alessio and Upfal, Eli},
booktitle = {International Conference on Machine Learning},
year = {2023},
pages = {24251-24270},
volume = {202},
url = {https://mlanthology.org/icml/2023/mazzetto2023icml-nonparametric/}
}