Hoeffding の確率不等式の性能向上のための数値解析的手法に関する研究

Translated title of the contribution: A numerical analysis procedure for improving performance of hoeffding probability inequality

Takumu Mitsuoka, Ikuo Arizono, Yasuhiko Takemoto

Research output: Contribution to journalArticlepeer-review

Abstract

Hoeffding probability inequality has been known as the best theoretical way for evaluating the upper bound of upper probability about the average of some random variables based on limited stochastic properties such as the expectation, variance and codomain in each random variable. In this study, based on Hoeffding probability inequality, we address a numerical analysis procedure for improving the performance to evaluate the upper bound of upper probability about the average of some random variables.

Translated title of the contributionA numerical analysis procedure for improving performance of hoeffding probability inequality
Original languageJapanese
Pages (from-to)76-79
Number of pages4
JournalJournal of Japan Industrial Management Association
Volume71
Issue number2
Publication statusPublished - 2020

ASJC Scopus subject areas

  • Strategy and Management
  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering
  • Applied Mathematics

Fingerprint Dive into the research topics of 'A numerical analysis procedure for improving performance of hoeffding probability inequality'. Together they form a unique fingerprint.

Cite this