We consider the problem of anomaly sequence detection under the general setting of unknown anomaly and anomaly-free models.  In particular, the anomaly time series is a stationary random process with unknown underlying probablitiy model.  The anomaly-free time series is also stationary but epsilon-distance away from all anomaly processes.  We present an approach that ties some of the classical problems in statistics, signal processing, and modern machine learning: innovations sequence, uniformity test, and generative adversary networks (GAN).

Lang Tong is the Irwin and Joan Jacobs Professor in Engineering and the Cornell site director of the Power Systems Engineering Research Center (PSERC). His current research focuses on energy and power systems, smart grids, and the electrification of transportation systems. His expertise lies in the intersection of data analytics, machine learning, optimization, and market design.  He received numerous publication awards from the IEEE Signal Processing, Communications, and Power and Energy System Societies.

Lang Tong received a B.E. degree from Tsinghua University and a Ph.D. degree from the University of Notre Dame. A Fellow of IEEE, he was the 2018 Fulbright Distinguished Chair in Alternative Energy.