Misspecified and Asymptotically Minimax Robust Quickest Change Diagnosis

The problem of quickly diagnosing an unknown change in a stochastic process is studied. We establish novel bounds on the performance misspecified diagnosis algorithms designed for changes that differ from those process, and pose solve new robust quickest asymptotic regime few false alarms isolations. Simulations suggest our asymptotically solution offers computationally efficient alternative to generalised likelihood ratio algorithms.