7 problems

The setting is sequential changepoint detection using a survival-analysis–based approach, including Kaplan–Meier estimators for average run length and detection delay. Extension co…

Let $G_n$ be the final snapshot of a preferential attachment network on $n$ vertices, and suppose the changepoint is in the late-change regime $\tau_n=n-\Delta$ with…

Asymptotic optimality conjecture. Asymptotic optimality properties hold for this multistream finite moving average detection procedure.

Let $\theta$ be a piecewise constant sequence, with $k$ denoting the model complexity or number of segments, and let the concentration rate describe the rate at which a Bayesian po…

Let $\widetilde{T}_B$ be the Shiryaev1 Roberts stopping time with threshold $B$, let $\mathsf{PFA}(\widetilde{T}_B)$ denote its probability of false alarm, and let $\mu\geq 0$ be t…

Let $r>0$, let $u$ be a changepoint with prior probabilities $boldsymbol{pi}=(boldsymbol{pi}0,boldsymbol{pi}1,boldsymbol{pi}2,u2026)$, and let $lambda{k+n}^k$ denote the log-likel…

Worst-changepoint-at-infinity conjecture. The worst changepoint for the SR-$r$ procedure is at infinity: the supremum of the conditional average detection delay over changepoints i…