High dimensional decision making, upper and lower bounds

DOI10.1016/J.ECONLET.2021.109894MaRDI QIDQ2036985zbMATH OpenOpenAlexFDO

Authors Farzad Pourbabaee

Publication date 30 June 2021

Published in Economics Letters (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2105.00545

zbMATH Keywords

decision makinghigh dimensional vectorsinformation valuation

Mathematics Subject Classification ID

Decision theory (91B06)

Abstract: A decision maker's utility depends on her action $ainAsubsetmathbb{R}^d$ and the payoff relevant state of the world $hetainTheta$. One can define the value of acquiring new information as the difference between the maximum expected utility pre- and post information acquisition. In this paper, I find asymptotic results on the expected value of information as $doinfty$, by using tools from the theory of (sub)-Guassian processes and generic chaining.

Recommendations

• Payoffs-beliefs duality and the value of information
• The value of a stochastic information structure
• Decreasing marginal value of information under symmetric loss
• The Law of Large Demand for Information
• The value of information -- an axiomatic approach

Cites work

• Coarse decision making and overfitting
• High-dimensional probability. An introduction with applications in data science
• Online decision making with high-dimensional covariates
• The Generic Chaining
• The K-armed bandit problem with multiple priors
• The sizes of compact subsets of Hilbert space and continuity of Gaussian processes
• Undescribable Events
• Upper and lower bounds for stochastic processes. Modern methods and classical problems

This page was built for publication: High dimensional decision making, upper and lower bounds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2036985)