2021/05/17 by Dániel Csaba, Csaba, Dániel
Computer Science · Decision Sciences · Economics, Econometrics and Finance · Mathematics · #Advanced Bandit Algorithms Research #Adversarial Robustness in Machine Learning #Certainty #Computer science #Econometrics #Economics #Elasticity (physics) #FOS: Economics and business #General Economics (econ.GN) #Generalization #Incentive #Invariant (physics) #Mathematical analysis #Mathematical economics #Mathematical optimization #Mathematics #Microeconomics #Minification #Stochastic Gradient Optimization Techniques #Theoretical Economics (econ.TH) #econ.GN #econ.TH #q-fin.EC
paper · pdf · doi:10.48550/arxiv.2105.07565
published in arXiv (Cornell University) (Cornell University)
arxiv created 2021/05/17 · openalex publication_date 2021/05/17 · arxiv updated 2021/05/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
We consider a generalization of rational inattention problems by measuring costs of information through the information radius (Sibson, 1969; Verdú, 2015) of statistical experiments. We introduce a notion of attention elasticity measuring the sensitivity of attention strategies with respect to changes in incentives. We show how the introduced class of cost functions controls attention elasticities while the Shannon model restricts attention elasticity to be unity. We explore further differences and similarities relative to the Shannon model in relation to invariance, posterior separability, consideration sets, and the ability to learn events with certainty. Lastly, we provide an efficient alternating minimization method -- analogous to the Blahut-Arimoto algorithm -- to obtain optimal attention strategies.