Optimal Regret Exponents for Bayesian Statistical Decision Problems
IEEE Signal Processing Letters · 2026 · 33 · 3112-3116
DOI: 10.1109/lsp.2026.3715442 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Hyun-Young Park und 1 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Gefördert von: Institute of Information & communications Technology Planning & Evaluation, Korea government, Korea Media and Communications Commission.
Abstract (Originalsprache)
We study finite-state finite-action Bayesian statistical decision problems. While exact error-exponent characterizations are known for several special cases, including hypothesis testing and hypothesis exclusion, the asymptotic behavior of the optimal Bayes regret is largely unknown for general decision problems. In this paper, we show that the optimal regret always decays exponentially fast and characterize its exact exponent for arbitrary loss functions. The exponent is given by the minimum multivariate Chernoff information over the minimal incompatible subsets of states, where an incompatible subset is a collection of states for which no single action is optimal for all states in the subset. Our result recovers the classical pairwise-minimum Chernoff exponent for symmetric multiple hypothesis testing and the multivariate Chernoff exponent for hypothesis exclusion, while also yielding, to the best of our knowledge, the first exact exponent characterization for list hypothesis testing.
Förderung
- Institute of Information & communications Technology Planning & Evaluation
- Korea government
- Korea Media and Communications Commission
Zitieren
APA
Park, H., & Lee, S. (2026). Optimal Regret Exponents for Bayesian Statistical Decision Problems. IEEE Signal Processing Letters, 33, 3112-3116. https://doi.org/10.1109/lsp.2026.3715442
Vancouver
Park H, Lee S. Optimal Regret Exponents for Bayesian Statistical Decision Problems. IEEE Signal Processing Letters. 2026;33:3112-3116. doi:10.1109/lsp.2026.3715442
BibTeX
@article{Park2026,
author = {Park, Hyun-Young and Lee, Si-Hyeon},
title = {Optimal Regret Exponents for Bayesian Statistical Decision Problems},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {3112--3116},
doi = {10.1109/lsp.2026.3715442}
}
EUVIMED