English

Sequential Controlled Sensing for Composite Multihypothesis Testing

Statistics Theory 2019-10-29 v1 Machine Learning Machine Learning Statistics Theory

Abstract

The problem of multi-hypothesis testing with controlled sensing of observations is considered. The distribution of observations collected under each control is assumed to follow a single-parameter exponential family distribution. The goal is to design a policy to find the true hypothesis with minimum expected delay while ensuring that the probability of error is below a given constraint. The decision-maker can control the delay by intelligently choosing the control for observation collection in each time slot. We derive a policy that satisfies the given constraint on the error probability. We also show that the policy is asymptotically optimal in the sense that it asymptotically achieves an information-theoretic lower bound on the expected delay.

Keywords

Cite

@article{arxiv.1910.12697,
  title  = {Sequential Controlled Sensing for Composite Multihypothesis Testing},
  author = {Aditya Deshmukh and Srikrishna Bhashyam and Venugopal V. Veeravalli},
  journal= {arXiv preprint arXiv:1910.12697},
  year   = {2019}
}