PreprintarXiv licencearXiv
Nearly-minimax variance estimation under rough random design
Abstract
We identify the minimax exponent for constant conditional variance estimation under rough random design. The unknown design density is bounded above and away from zero, with no smoothness assumption, and the conditional error laws may depend on the covariates and have uniformly bounded fourth moments. For an s-Hölder regression function with s>1 in dimension d>4s, the minimax root-mean-square risk lies between cn−2(s+1)/(d+4)e−C√(log n) and Cn−2(s+1)/(d+4). These bounds show that the rate proposed by Robins is not uniformly attainable over this model class. For 0<s≤1, we show the exact minimax rate is n−1/2∨ n−4s/(d+4s); for s>1 and d≤4s, it is n−1/2.
Related
- Improved Variance Estimation in Homoskedastic Nonparametric Random-Design Regression via a Two-Scale Approach
- Minimax rates for pointwise CATE estimation: the role of design smoothness
- Spherical-Design Oracles for Zeroth-Order Optimisation: Deterministic, Variance-Free Gradient Estimation
- Nonparametric Regression on Fixed-Cardinality Subsets:Minimax Risk and Random-Design Effects
- Model-assisted estimation with a training subsample: a two-phase sampling approach with design-based variance estimation
BibTeX
@misc{aronow2026nearlyminimax,
title = {{Nearly-minimax variance estimation under rough random design}},
author = {P. M. Aronow and Patrick Lopatto},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2607.13170},
eprint = {2607.13170},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.13170},
}
RIS
TY - UNPB
TI - Nearly-minimax variance estimation under rough random design
AU - P. M. Aronow
AU - Patrick Lopatto
PY - 2026
DA - 2026/09/09
PB - arXiv
DO - 10.48550/arxiv.2607.13170
UR - https://arxiv.org/abs/2607.13170
AB - We identify the minimax exponent for constant conditional variance estimation under rough random design. The unknown design density is bounded above and away from zero, with no smoothness assumption, and the conditional error laws may depend on the covariates and have uniformly bounded fourth moments. For an s-Hölder regression function with s>1 in dimension d>4s, the minimax root-mean-square risk lies between cn^−2(s+1)/(d+4)e^−C√(log n) and Cn^−2(s+1)/(d+4). These bounds show that the rate proposed by Robins is not uniformly attainable over this model class. For 0<s≤1, we show the exact minimax rate is n^−1/2∨ n^−4s/(d+4s); for s>1 and d≤4s, it is n^−1/2.
ER -