English

High Dimensional Decision Making, Upper and Lower Bounds

Theoretical Economics 2021-05-04 v1 Machine Learning

Abstract

A decision maker's utility depends on her action aARda\in A \subset \mathbb{R}^d and the payoff relevant state of the world θΘ\theta\in \Theta. 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 dd \to \infty, by using tools from the theory of (sub)-Guassian processes and generic chaining.

Keywords

Cite

@article{arxiv.2105.00545,
  title  = {High Dimensional Decision Making, Upper and Lower Bounds},
  author = {Farzad Pourbabaee},
  journal= {arXiv preprint arXiv:2105.00545},
  year   = {2021}
}
R2 v1 2026-06-24T01:42:53.214Z