Finite Sample Bounds for Composite Hypothesis Testing
Abstract
We investigate composite binary hypothesis testing in the finite sample regime under asymmetric error constraints. Using Rényi divergences, we derive explicit achievability and converse bounds for the optimal Type II error. When the Type I error is constrained to decay exponentially with sample size, the bounds identify a phase transition and yield a strong converse above it. In the composite problem, the phase transition threshold is given by the joint KL projection over the alternative and null classes. Achievability is obtained through a joint Rényi projection whose log likelihood ratio defines a single test with uniform error control over both hypothesis classes, without requiring the projected pair to be least favourable. For compact convex classes with full support on a finite alphabet, we determine the exact error exponents on both sides of the transition and show that the achievable exponent is attained at a unique Rényi order. The same framework recovers the fixed Type I composite Chernoff--Stein exponent and yields a polynomial refinement of the finite sample achievability result. We further identify conditions under which the projected pair is least favourable at finite sample size.
Related
- Finite-Sample Binary Hypothesis Testing via Rényi Divergences: Strong Converse and Local Privacy
- PDE-Based Bounds on Optimal Exponents in Active Simple Hypothesis Testing
- Accumulated-Variance Functionals of Hidden Markov and Semi-Markov Processes: Finite-Sample Upper and Lower Bounds
- Finite-Sample Hausdorff Bounds and Hadamard Sensitivity for Regressions with MNAR Covariates
- Asymptotics and finite sample bounds for prediction and smoothing in Wright-Fisher hidden Markov models
BibTeX
@misc{verasiguenza2026finite,
title = {{Finite Sample Bounds for Composite Hypothesis Testing}},
author = {Elías Vera-Sigüenza and Amedeo Roberto Esposito},
howpublished = {arXiv},
year = {2026},
month = aug,
doi = {10.48550/arxiv.2608.28068},
eprint = {2608.28068},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.28068},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Finite Sample Bounds for Composite Hypothesis Testing
AU - Elías Vera-Sigüenza
AU - Amedeo Roberto Esposito
PY - 2026
DA - 2026/08/31
PB - arXiv
DO - 10.48550/arxiv.2608.28068
UR - https://arxiv.org/abs/2608.28068
AB - We investigate composite binary hypothesis testing in the finite sample regime under asymmetric error constraints. Using Rényi divergences, we derive explicit achievability and converse bounds for the optimal Type II error. When the Type I error is constrained to decay exponentially with sample size, the bounds identify a phase transition and yield a strong converse above it. In the composite problem, the phase transition threshold is given by the joint KL projection over the alternative and null classes. Achievability is obtained through a joint Rényi projection whose log likelihood ratio defines a single test with uniform error control over both hypothesis classes, without requiring the projected pair to be least favourable. For compact convex classes with full support on a finite alphabet, we determine the exact error exponents on both sides of the transition and show that the achievable exponent is attained at a unique Rényi order. The same framework recovers the fixed Type I composite Chernoff--Stein exponent and yields a polynomial refinement of the finite sample achievability result. We further identify conditions under which the projected pair is least favourable at finite sample size.
ER -