Minimax Additive Regression under Unknown Dependent Designs
Abstract
We study additive regression under an unknown and potentially non product design distribution, allowing the number of covariates to grow with the sample size. We consider a coupled class that separately controls the smoothness of the marginal densities and of each additive component multiplied by the corresponding marginal density. Under joint-density bounds that hold uniformly in the dimension and suitable dimension-growth conditions, we establish matching minimax bounds for prediction. With known marginal densities, the classical additive rate is attainable. When the marginals are unknown, this rate is preserved if the densities are at least as smooth as the weighted components. Otherwise, marginal-density smoothness determines the minimax rate over the coupled class. Finally, we recover all additive components with total squared error of the same order as the prediction error.
Related
- Pointwise minimax lower bounds under a multi-index constraint: the price of an unknown orientation
- A Method of Construction of Pairwise Additive Balanced Incomplete Block Designs
- Robust Local Fréchet Regression: Nonasymptotic Theory and Minimax Optimality
- Conformalized Quantile Regression and Minimax Limits of Fixed-Score Calibration under Known Covariate Shift
- Flexible covariate adjustments in regression discontinuity designs
BibTeX
@misc{ferrere2026minimax,
title = {{Minimax Additive Regression under Unknown Dependent Designs}},
author = {Baptiste Ferrere and Fabrice Gamboa and Jean-Michel Loubes},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.39212},
eprint = {2609.39212},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.39212},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Minimax Additive Regression under Unknown Dependent Designs
AU - Baptiste Ferrere
AU - Fabrice Gamboa
AU - Jean-Michel Loubes
PY - 2026
DA - 2026/10/03
PB - arXiv
DO - 10.48550/arxiv.2609.39212
UR - https://arxiv.org/abs/2609.39212
AB - We study additive regression under an unknown and potentially non product design distribution, allowing the number of covariates to grow with the sample size. We consider a coupled class that separately controls the smoothness of the marginal densities and of each additive component multiplied by the corresponding marginal density. Under joint-density bounds that hold uniformly in the dimension and suitable dimension-growth conditions, we establish matching minimax bounds for prediction. With known marginal densities, the classical additive rate is attainable. When the marginals are unknown, this rate is preserved if the densities are at least as smooth as the weighted components. Otherwise, marginal-density smoothness determines the minimax rate over the coupled class. Finally, we recover all additive components with total squared error of the same order as the prediction error.
ER -