The paper derives a robust objective for Bayesian experimental design governed by Sibson's α-mutual information and provides PAC-Bayes lower bounds on the robust expected information gain.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Maximin Robust Bayesian Experimental Design
The paper derives a robust objective for Bayesian experimental design governed by Sibson's α-mutual information and provides PAC-Bayes lower bounds on the robust expected information gain.