Gaussian-efficient testing by betting on the mean of bounded data
Abstract
Given [0,1]-valued random variables X1,…,Xn such that 𝔼[Xi | X1,…,Xi−1]= μ for all i, we propose a new nonasymptotic confidence interval for μ that is obtained by inverting terminal e-values generated by a novel betting strategy. When the data are iid, its limiting width matches that of the central limit theorem (``Gaussian-efficient''), finally surpassing the inefficient limits of previous betting intervals. Our main conceptual advance involves designing betting fractions that track the conditional rejection probability of the most powerful terminal test in a limiting Gaussian experiment. When one predictable variance estimator is shared across candidate means, the deterministic inversion is an interval for every data sequence and its two endpoints can be found easily. The width can be improved further with external randomization. In simulations, our method yields the tightest intervals to date; for every distribution tested and all sufficiently large n, our deterministic version beats STaR-Bets and is competitive with Gaffke, while the randomized improvement beats both. It thus combines finite-sample validity under martingale dependence, easy endpoint computation, Gaussian-efficient inference for iid data, and excellent empirical performance. We further combine GE-betting with a mixture of constant-fraction bets to attain both Gaussian and large-deviation efficiency under iid sampling while retaining martingale validity. We also extend the construction and its efficiency theory to sampling without replacement, where it again achieves state-of-the-art empirical performance.
Related
- Optimal Priors for Betting Tests with Bounded Payoffs: An Exact Expected-Time Characterization
- Competitive optimality in testing by betting via Bell-Cover randomization
- Singularities of Mean Curvature Flow with Bounded Total Curvature
- Bounded curvature manifolds without Euclidean isometric immersions of bounded mean curvature
- Existence of Lagrangian Mean Curvature Flow Singularities with Bounded Mean Curvature
BibTeX
@misc{martineztaboada2026gaussianefficient,
title = {{Gaussian-efficient testing by betting on the mean of bounded data}},
author = {Diego Martinez-Taboada and Aaditya Ramdas},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2608.21694},
eprint = {2608.21694},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.21694},
}
RIS
TY - UNPB
TI - Gaussian-efficient testing by betting on the mean of bounded data
AU - Diego Martinez-Taboada
AU - Aaditya Ramdas
PY - 2026
DA - 2026/10/30
PB - arXiv
DO - 10.48550/arxiv.2608.21694
UR - https://arxiv.org/abs/2608.21694
AB - Given [0,1]-valued random variables X_1,…,X_n such that 𝔼[X_i | X_1,…,X_i−1]= μ for all i, we propose a new nonasymptotic confidence interval for μ that is obtained by inverting terminal e-values generated by a novel betting strategy. When the data are iid, its limiting width matches that of the central limit theorem (``Gaussian-efficient''), finally surpassing the inefficient limits of previous betting intervals. Our main conceptual advance involves designing betting fractions that track the conditional rejection probability of the most powerful terminal test in a limiting Gaussian experiment. When one predictable variance estimator is shared across candidate means, the deterministic inversion is an interval for every data sequence and its two endpoints can be found easily. The width can be improved further with external randomization. In simulations, our method yields the tightest intervals to date; for every distribution tested and all sufficiently large n, our deterministic version beats STaR-Bets and is competitive with Gaffke, while the randomized improvement beats both. It thus combines finite-sample validity under martingale dependence, easy endpoint computation, Gaussian-efficient inference for iid data, and excellent empirical performance. We further combine GE-betting with a mixture of constant-fraction bets to attain both Gaussian and large-deviation efficiency under iid sampling while retaining martingale validity. We also extend the construction and its efficiency theory to sampling without replacement, where it again achieves state-of-the-art empirical performance.
ER -