Yi Zhou, Parikshit Ram, et al.
ICLR 2023
A change-point model is considered where the canonical parameter of an exponential family drifts from its control value at an unknown time and changes according to a broken-line regression. Necessary and sufficient conditions are obtained for the existence of consistent change-point estimators. When sufficient conditions are met, it is shown that the maximum likelihood estimator of the change point is consistent, unlike the classical abrupt change-point models. Results are extended to the case of nonlinear trends and nonequidistant observations. © 2003 Elsevier B.V. All rights reserved.
Yi Zhou, Parikshit Ram, et al.
ICLR 2023
William Hinsberg, Joy Cheng, et al.
SPIE Advanced Lithography 2010
John R. Kender, Rick Kjeldsen
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shu Tezuka
WSC 1991