Active Hypothesis Testing: Beyond Chernoff-Stein
Active Hypothesis Testing: Beyond Chernoff-Stein
复制标题
主动假设检验：超越 Chernoff-Stein
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
U. Mitra
中科院分区：
文献类型：
--
作者：
D. Kartik;A. Nayyar;U. Mitra
提出了一个主动假设检验问题。在这个问题中，智能体可以执行固定数量的实验，然后决定其中一个假设。如果需要的话，代理人也可以宣布其实验是不确定的。目标是最大限度地减少做出不正确推断的概率（误分类概率），同时确保以适度高的概率最终声明真实的假设。对于这个问题，上下限的最佳误分类概率的推导和这些界限是渐近紧。在分析中，一个子问题，它可以被看作是一个推广的Besoff-Stein引理，制定和分析。提出了一种启发式策略设计方法，并讨论了它与现有启发式策略的关系。
An active hypothesis testing problem is formulated. In this problem, the agent can perform a fixed number of experiments and then decide on one of the hypotheses. The agent is also allowed to declare its experiments inconclusive if needed. The objective is to minimize the probability of making an incorrect inference (misclassification probability) while ensuring that the true hypothesis is declared conclusively with moderately high probability. For this problem, lower and upper bounds on the optimal misclassification probability are derived and these bounds are shown to be asymptotically tight. In the analysis, a sub-problem, which can be viewed as a generalization of the Chernoff-Stein lemma, is formulated and analyzed. A heuristic approach to strategy design is proposed and its relationship with existing heuristic strategies is discussed.