Minimax Renyi Redundancy

被引：4
|
作者：
Yagli, Semih [1 ]
Altug, Yucel [2 ]
Verdu, Sergio [1 ]
机构：
[1] Princeton Univ, Dept Elect Engn, Princeton, NJ 08544 USA
[2] Natera Inc, San Carlos, CA 94070 USA
来源：
IEEE TRANSACTIONS ON INFORMATION THEORY | 2018年 / 64卷 / 05期
基金：
美国国家科学基金会;
关键词：
Universal lossless compression; generalized redundancy-capacity theorem; minimax redundancy; minimax regret; Jeffreys' prior; risk aversion; Renyi divergence; alpha-mutual information; DATA-COMPRESSION; RISK-AVERSION; INFORMATION; ASYMPTOTICS; STRATEGIES;
D O I：
10.1109/TIT.2018.2803070
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
The redundancy for universal lossless compression of discrete memoryless sources in Campbell's setting is characterized as a minimax Renyi divergence, which is shown to be equal to the maximal alpha-mutual information via a generalized redundancy-capacity theorem. Special attention is placed on the analysis of the asymptotics of minimax Renyi divergence, which is determined up to a term vanishing in blocklength.
引用
收藏
页码：3715 / 3733
页数：19
相关论文
共 50 条
12345