Adversarially robust sequential hypothesis testing
Adversarially robust sequential hypothesis testing
复制标题
对抗性稳健序贯假设检验
DOI：
10.1080/07474946.2022.2043050
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Zou, Shaofeng
中科院分区：
文献类型：
--
作者：
Cao, Shuchen;Zhang, Ruizhi;Zou, Shaofeng
研究了序贯假设检验问题，其中样本是序贯采集的，目标是区分样本是按分布p生成的零假设和样本是按分布q生成的备择假设.防御者（决策者）的目标是区分两个假设，使用尽可能少的样本受到虚警约束。该问题是在对抗性设置下研究的，在这两个假设下的数据生成分布被对手操纵，其目标是以最小的成本恶化防御者的性能，例如，增加错误的概率和预期的样本大小。具体地说，在零假设下，对手选择一个有成本的分布，在备择假设下，对手选择一个有成本的分布。这个问题被表述为防御者和对手之间的非零和博弈。提出了一对策略（对手策略和防守者策略），并证明了这对策略是对手和防守者之间非零和博弈的纳什均衡对。防御者的策略是一个序贯概率比测试，因此在实际执行中计算效率很高。
The problem of sequential hypothesis testing is studied, where samples are taken sequentially, and the goal is to distinguish between the null hypothesis where the samples are generated according to a distributionpand the alternative hypothesis where the samples are generated according to a distributionq. The defender (decision maker) aims to distinguish the two hypotheses using as few samples as possible subject to false alarm constraints. The problem is studied under the adversarial setting, where the data generating distributions under the two hypotheses are manipulated by an adversary, whose goal is to deteriorate the performance of the defender—for example, increasing the probability of error and expected sample sizes—with minimal cost. Specifically, under the null hypothesis, the adversary picks a distributionwith costand under the alternative hypothesis, the adversary picks a distributionwith costThis problem is formulated as a non-zero-sum game between the defender and the adversary. A pair of strategies (the adversary’s strategy and the defender’s strategy) is proposed and proved to be a Nash equilibrium pair for the non-zero-sum game between the adversary and the defender asymptotically. The defender’s strategy is a sequential probability ratio test and thus is computationally efficient for practical implementation.
登录
查看更多内容
高效的拜占庭顺序变化检测
影响因子：
2.5
作者：
Fellouris, Georgios;Bayraktar, Erhan;Lai, Lifeng
通讯作者：
Lai, Lifeng
影响因子：
3
作者：
A. Tartakovsky;I. Nikiforov;M. Basseville
通讯作者：
A. Tartakovsky;I. Nikiforov;M. Basseville
Minimax鲁棒分散检测
影响因子：
2.5
作者：
V. Veeravalli;T. Başar;H. Poor
通讯作者：
H. Poor
DOI：
--
发表时间：
2019
期刊：
International Symposium on Information Theory
影响因子：
--
作者：
Yu‐Jui Huang;Shih;Yu
通讯作者：
Yu
错误指定和渐近极小极大稳健最快变化检测
影响因子：
5.4
作者：
Timothy L. Molloy;J. Ford
通讯作者：
J. Ford