Adaptive Active Hypothesis Testing under Limited Information
We consider the problem of active sequential hypothesis testing where a Bayesian decision maker must infer the true hypothesis from a set of hypotheses. The decision maker may choose for a set of actions, where the outcome of an action is corrupted by independent noise. In this paper we consider a special case where the decision maker has limited knowledge about the distribution of observations for each action, in that only a binary value is observed. Our objective is to infer the true hypothesis with low error, while minimizing the number of action sampled. Our main results include the derivation of a lower bound on sample size for our system under limited knowledge and the design of an active learning policy that matches this lower bound and outperforms similar known algorithms.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningTwo-sample testingSimilar Papers 제목 키워드 기반
Sequential Experiment Design for Hypothesis Verification
Hypothesis testing is an important problem with applications in target localization, clinical trials etc. Many active hypothesis testing strategies operate in two phases: an exploration phase and a verification phase. In…
Two-sample testingActive Hypothesis Testing for Correlated Combinatorial Anomaly Detection
We study the problem of identifying an anomalous subset of streams under correlated noise, motivated by monitoring and security in cyber-physical systems. This problem can be viewed as a form of combinatorial pure explor…
Anomaly DetectionThe Role of Interactivity in Local Differential Privacy
We study the power of interactivity in local differential privacy. First, we focus on the difference between fully interactive and sequentially interactive protocols. Sequentially interactive protocols may query users ad…
Two-sample testingPolicy Design for Active Sequential Hypothesis Testing using Deep Learning
Information theory has been very successful in obtaining performance limits for various problems such as communication, compression and hypothesis testing. Likewise, stochastic control theory provides a characterization …
Deep LearningDeep Reinforcement LearningReinforcement LearningTwo-sample testingFinite-Sample Analysis of Elimination in Active Hypothesis Testing
A fixed-confidence, finite-sample problem of active hypothesis testing arises in many safety-critical applications. Situated in the context of sequential hypothesis testing, this paper studies the effect of hypothesis el…