Improved Bounds on the Moments of Guessing Cost
2022 IEEE International Symposium on Information Theory, ISIT 2022, Espoo, Finlandiya, 26 Haziran - 01 Temmuz 2022, cilt.2022-June, ss.3351-3356, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Cilt numarası: 2022-June
- Doi Numarası: 10.1109/isit50566.2022.9834714
- Basıldığı Şehir: Espoo
- Basıldığı Ülke: Finlandiya
- Sayfa Sayıları: ss.3351-3356
- Boğaziçi Üniversitesi Adresli: Hayır
Özet
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.