The paper proves sharp O(ε² log(1/ε)/log log(1/ε)) regret bounds for unregularized Bayes rules with compactly supported priors via polynomial approximation, improving on prior regularized results with extra log factors.
arXiv preprint arXiv:2602.20115 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
A nonparametric quasi-Bayes empirical Bayes procedure is proposed for estimating sums of random variables, with recursive mixing distribution estimation, asymptotic guarantees, and uncertainty quantification.
Proves frequentist merging of Bayesian (Dirichlet process) and quasi-Bayesian (Newton's algorithm) empirical Bayes estimators for Poisson compound decisions via concentration rates on marginal PMFs and excess risks, with multidimensional extension.
citing papers explorer
-
Sharp regret-Hellinger bounds for Gaussian empirical Bayes via polynomial approximation
The paper proves sharp O(ε² log(1/ε)/log log(1/ε)) regret bounds for unregularized Bayes rules with compactly supported priors via polynomial approximation, improving on prior regularized results with extra log factors.