
TL;DR
This paper introduces a weighted garbling order for experiments, providing a new way to compare their informativeness based on posterior beliefs and decision-theoretic criteria.
Contribution
It generalizes the concept of garbling, characterizes the order via posterior support, and offers decision-theoretic characterizations in static and dynamic settings.
Findings
Weighted garbling order depends only on posterior support.
An experiment dominates another if it provides a higher value of information across problems.
Dominance in dynamic problems aligns with higher expected payoffs for all priors.
Abstract
We introduce an information order on experiments based on weighted garbling, a generalization of the standard notion of garbling. In this order, an experiment is more informative than another if the latter is a weighted garbling of the former. We show that this is equivalent to ordinary garbling conditional on a payoff-irrelevant event. We also characterize the order in terms of induced posterior belief distributions, showing that it depends only on their support. Our main results provide two decision-theoretic characterizations of this order. First, in static decision problems, one experiment dominates another if and only if its value of information is at least a fixed fraction of the other's across all problems. Second, in a class of stopping time problems with a hidden Markov process and repeated experimentation, one experiment dominates another if and only if it yields weakly higher…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Bandit Algorithms Research · Decision-Making and Behavioral Economics · Auction Theory and Applications
