Convex, sub-additive information costs are exactly maxima of extended Renyi divergences, and the linear special case recovers posterior-separable KL costs.
Experimental cost of information,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
econ.TH 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Convex Cost of Information via Statistical Divergence
Convex, sub-additive information costs are exactly maxima of extended Renyi divergences, and the linear special case recovers posterior-separable KL costs.