Minimax robust quickest change detection in systems and signals with unknown transients

We consider the problem of quickly detecting an unknown change in a sequence of independent random variables with unknown transient (or time-varying) pre-change and post-change distributions. We pose and solve novel robust versions of the popular Lorden and Bayesian quickest change detection criteria with unknown transients that belong to known uncertainty sets. Simulations of our robust solutions detecting additive changes in linear state-space systems suggest that they can outperform more computationally expensive rules.