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.
Concentration of Measure Inequalities in Information Theory, Communications, and Coding , Volume =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.