Abstract: Gaussian graphical model selection is usually studied under independent sampling, but in many applications the data arise as a single trajectory of a dependent stochastic process. In this talk, I will consider the exact recovery of a graph from one trajectory of random-scan Gaussian Glauber dynamics. Existing techniques for this problem either inherit the mixing time of the chain, which can be super-polynomial in the dimension p without strong assumptions, or are suboptimal in the minimum normalized edge strength κ. We propose two algorithms that are mixing-free and attain the 1/κ^2 dependence of the information-theoretic lower bounds. Both instantiate a shared dueling-neighborhood search meta-algorithm with a local statistic built directly from the update sequence. The central technical challenge is that both statistics are built from dependent, non-stationary observations. Our analysis tackles this by demonstrating how to extract fresh Gaussian innovations from the update sequence, which yields mixing-free control of appropriate quantities. Neither the algorithms nor their analyses invoke stationarity, a spectral gap, or mixing conditions. If time permits, I will end with some open problems and connections to multi-agent systems and system identification. Based on joint work with Vignesh Tirukkonda.

Bio: Gautam Dasarathy is an Associate Professor in ECEE at Arizona State University. His research focuses on statistical machine learning, information processing, and networked systems. He received his Ph.D. from the University of Wisconsin-Madison and held postdoctoral positions at Carnegie Mellon University and Rice University. Dr. Dasarathy received the NSF CAREER Award in 2021, the Distinguished Alumnus Award from VIT University (India) in 2022, and was an Amazon Scholar in Amazon Last Mile Sciences in 2025.