Improved Bounds on the Moments of Guessing Cost

Guessing a random variable with finite or countably infinite support in which each selection leads to a positive cost value has recently been studied within the context of "guessing cost". In those studies, similar to standard guesswork, upper and lower bounds for the ρ-th moment of guessi...

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE International Symposium on Information Theory (ISIT) pp. 3351 - 3356
Main Authors Arslan, Suayb S., Haytaoglu, Elif
Format Conference Proceeding
LanguageEnglish
Published IEEE 26.06.2022
Subjects
Costs
Entropy
Information theory
Random variables
Upper bound
Online AccessGet full text

Cover

More Information
Summary:Guessing a random variable with finite or countably infinite support in which each selection leads to a positive cost value has recently been studied within the context of "guessing cost". In those studies, similar to standard guesswork, upper and lower bounds for the ρ-th moment of guessing cost are described in terms of the known measure Rényi's entropy. In this study, we non-trivially improve the known bounds using previous techniques along with new notions such as balancing cost. We have demonstrated that the novel lower bound proposed in this work, achieves 5.84%, 18.47% higher values than that of the known lower bound for ρ = 1 and ρ = 5, respectively. As for the upper bound, the novel expression provides 10.93%, 5.54% lower values than that of the previously presented bounds for ρ = 1 and ρ = 5, respectively.
ISSN:2157-8117
DOI:10.1109/ISIT50566.2022.9834714