Bayesian sequential joint detection and estimation under multiple hypotheses

DOI10.1080/07474946.2022.2043053zbMATH Open1493.62486arXiv2003.12405OpenAlexW3013671361WikidataQ114639456 ScholiaQ114639456MaRDI QIDQ5089388FDOQ5089388

Dominik Reinhard, Michael Fauß, Abdelhak M. Zoubir

Publication date: 19 July 2022

Published in: Sequential Analysis (Search for Journal in Brave)

Abstract: We consider the problem of jointly testing multiple hypotheses and estimating a random parameter of the underlying distribution. This problem is investigated in a sequential setup under mild assumptions on the underlying random process. The optimal method minimizes the expected number of samples while ensuring that the average detection/estimation errors do not exceed a certain level. After converting the constrained problem to an unconstrained one, we characterize the general solution by a non-linear Bellman equation, which is parametrized by a set of cost coefficients. A strong connection between the derivatives of the cost function with respect to the coefficients and the detection/estimation errors of the sequential procedure is derived. Based on this fundamental property, we further show that for suitably chosen cost coefficients the solutions of the constrained and the unconstrained problem coincide. We present two approaches to finding the optimal coefficients. For the first approach, the final optimization problem is converted into a linear program, whereas the second approach solves it with a projected gradient ascent. To illustrate the theoretical results, we consider two problems for which the optimal schemes are designed numerically. Using Monte Carlo simulations, it is validated that the numerical results agree with the theory.

Full work available at URL: https://arxiv.org/abs/2003.12405

Recommendations

• Bayesian sequential joint detection and estimation
• A linear programming approach to sequential hypothesis testing
• Sequential joint detection and estimation
• Optimal sequential multiple hypothesis tests
• Joint statistical signal detection and estimation. I: Theoretical aspects of the problem.

zbMATH Keywords

sequential analysisstopping timemultiple hypothesesjoint detection and estimation

Mathematics Subject Classification ID

Sequential statistical analysis (62L10) Linear programming (90C05) Sequential estimation (62L12) Optimal stopping in statistics (62L15) Estimation and detection in stochastic control theory (93E10)

Cites Work

• Title not available (Why is that?)
• Graph Implementations for Nonsmooth Convex Programs
• Title not available (Why is that?)
• Measure and integration theory. Transl. from the German by Robert B. Burckel
• Title not available (Why is that?)
• Joint Detection and Estimation of Multiple Objects From Image Observations
• A sequential procedure for multihypothesis testing
• Bayesian Reasoning and Machine Learning
• Sequential Detection of Markov Targets With Trajectory Estimation
• Optimal sequential multiple hypothesis tests
• Asymptotic optimality of certain multihypothesis sequential tests: Non-i. i. d. case
• Title not available (Why is that?)
• Title not available (Why is that?)
• Sequential Joint Detection and Estimation
• Bayesian sequential joint detection and estimation
• Joint Detection and Estimation: Optimum Tests and Applications
• Optimal Sequential Tests for Two Simple Hypotheses
• Simultaneous optimum detection and estimation of signals in noise
• Sequential Joint Detection and Estimation: Optimum Tests and Applications
• A Linear Programming Approach to Sequential Hypothesis Testing
• Simultaneous signal detection and estimation under multiple hypotheses
• Minimax-Optimal Hypothesis Testing With Estimation-Dependent Costs
• Optimal Joint Detection and Estimation Based on Decision-Dependent Bayesian Cost
• Sufficient statistics and reproducing densities in simultaneous sequential detection and estimation

Cited In (5)

• Bayesian sequential joint detection and estimation
• Joint statistical signal detection and estimation. I: Theoretical aspects of the problem.
• Feasible joint posterior beliefs with binary signals
• Optimal simultaneous detection and estimation under a false alarm constraint
• A Bayesian generalized CAR model for correlated signal detection

This page was built for publication: Bayesian sequential joint detection and estimation under multiple hypotheses

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5089388)