State Compression of Markov Processes via Empirical Low-Rank Estimation

Dimension reduction is a central problem in system engineering and data science. In scientific studies or engineering applications, one often needs to interact with unknown complex systems about which many noisy observations of system characteristics and system trajectories are available. The exact structures and dynamics of the system are typically masked by massive observations of noisy variables, many of which might not be relevant to the physical state of the system. It is often unclear how to describe the "state" of a system, when one can only access noisy observations. One may view each unique observation as a single state, however, this would generate a huge-or even infinite-dimensional process which is difficult to model or analyze. Although there exists a vast body of literatures on time series analysis [18], they typically require knowledge of specific models and might perform poorly when the models are misspecified. Anru Zhang is Assistant Professor, Department of Statistics, University of Wisconsin-Madison, Madison, WI 53706, Email: anruzhang@stat.wisc.edu; Mengdi Wang is Assistant Professor, Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ 08544, Email: mengdiw@princeton.edu.