2000 character limit reached
Information-theoretic convergence of extreme values to the Gumbel distribution (2007.03569v2)
Published 7 Jul 2020 in math.ST, cs.IT, math.IT, and stat.TH
Abstract: We show how convergence to the Gumbel distribution in an extreme value setting can be understood in an information-theoretic sense. We introduce a new type of score function which behaves well under the maximum operation, and which implies simple expressions for entropy and relative entropy. We show that, assuming certain properties of the von Mises representation, convergence to the Gumbel can be proved in the strong sense of relative entropy.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.