Nonzero-sum Adversarial Hypothesis Testing Games
Nonzero-sum Adversarial Hypothesis Testing Games
复制标题
非零和对抗性假设检验博弈
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
P. Loiseau
中科院分区：
文献类型：
--
作者：
S. Yasodharan;P. Loiseau
我们研究了在对抗分类的背景下出现的非零和假设检验游戏，在贝叶斯框架和Neyman-Pearson框架中。我们首先表明，这些游戏承认混合策略纳什均衡，然后我们研究了一些有趣的集中现象，这些均衡。我们的主要结果是指数收敛率的分类错误在平衡，这是类似于著名的Baffff-Stein引理和Baffff信息描述的错误指数在经典的二元假设检验问题，但参数来自对抗模型。通过数值实验验证了结果。
We study nonzero-sum hypothesis testing games that arise in the context of adversarial classification, in both the Bayesian as well as the Neyman-Pearson frameworks. We first show that these games admit mixed strategy Nash equilibria, and then we examine some interesting concentration phenomena of these equilibria. Our main results are on the exponential rates of convergence of classification errors at equilibrium, which are analogous to the well-known Chernoff-Stein lemma and Chernoff information that describe the error exponents in the classical binary hypothesis testing problem, but with parameters derived from the adversarial model. The results are validated through numerical experiments.
DOI：
10.1145/2020408.2020495
发表时间：
2011-08
期刊：
--
影响因子：
--
作者：
Michael Brückner;T. Scheffer
通讯作者：
Michael Brückner;T. Scheffer