Minimax Rates for Learning Smooth Populations of Parameters
Abstract
We study pointwise estimation of a smooth binomial mixing density and characterize its minimax rates. Assuming that the mixing density is s-Hölder smooth, we first consider the homogeneous setting with a common number of binomial trials t. We derive matching lower and upper bounds that reveal three regimes depending on the relative sizes of the sample size n and the number of trials t. When t is small, the finite number of trials creates an identification barrier that persists regardless of sample size; at intermediate t, more data reduce sampling uncertainty, while the number of trials limits how finely the mixing density can be recovered; and when t is sufficiently large, the usual nonparametric density estimation rate is recovered. Our lower bounds exploit the polynomial structure of the binomial mixture model, while attainability is achieved by a suitably regularized orthogonal series estimator. We then extend the analysis to heterogeneous trial parameters, where the minimax rate depends on the full trial profile through the effective sample size available at each polynomial degree. These results characterize the fundamental statistical limits of learning smooth populations of binomial probabilities under both homogeneous and heterogeneous trials.
Related
- Sharp Minimax Rates for Highly Smooth Strongly Convex Zeroth-Order Optimization
- Minimax rates for learning spectral Barron functions by deep ReLU neural networks
- Minimax Rates for Conditional Generative Learning under Wasserstein Loss
- Reinforcement Learning for Hierarchical Reasoning Rewards: Minimax-Optimal Rates with Transformers
- Near-Minimax-Optimal Rates for Asynchronous TD Learning with Markovian Data
BibTeX
@misc{lee2026minimax,
title = {{Minimax Rates for Learning Smooth Populations of Parameters}},
author = {JungHo Lee and Edward H. Kennedy},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.04135},
eprint = {2610.04135},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.04135},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Minimax Rates for Learning Smooth Populations of Parameters
AU - JungHo Lee
AU - Edward H. Kennedy
PY - 2026
DA - 2026/10/09
PB - arXiv
DO - 10.48550/arxiv.2610.04135
UR - https://arxiv.org/abs/2610.04135
AB - We study pointwise estimation of a smooth binomial mixing density and characterize its minimax rates. Assuming that the mixing density is s-Hölder smooth, we first consider the homogeneous setting with a common number of binomial trials t. We derive matching lower and upper bounds that reveal three regimes depending on the relative sizes of the sample size n and the number of trials t. When t is small, the finite number of trials creates an identification barrier that persists regardless of sample size; at intermediate t, more data reduce sampling uncertainty, while the number of trials limits how finely the mixing density can be recovered; and when t is sufficiently large, the usual nonparametric density estimation rate is recovered. Our lower bounds exploit the polynomial structure of the binomial mixture model, while attainability is achieved by a suitably regularized orthogonal series estimator. We then extend the analysis to heterogeneous trial parameters, where the minimax rate depends on the full trial profile through the effective sample size available at each polynomial degree. These results characterize the fundamental statistical limits of learning smooth populations of binomial probabilities under both homogeneous and heterogeneous trials.
ER -