Dr. Tian-Yi Zhou is a Postdoctoral Research Scientist in the Data Science Institute, where she is part of the 8th cohort of the DSI Postdoctoral Fellows Program. Her research focuses on deep learning theory, statistical learning theory, cybersecurity, anomaly detection, functional data analysis, and computational sociology.
Under the guidance of Professor Qiang Du and Professor Samory Kpotufe, Dr. Zhou will develop theoretically-governed neural network architectures for learning nonlinear operators between reproducing kernel Hilbert spaces (RKHSs). Her work will also involve using neural networks to model the regression map of function-to-function regression, where both input covariates and output responses lie in RKHSs. In addition, she will explore the application of operator learning to meta-learning, with a particular focus on anomaly detection in cybersecurity contexts.
Before joining Columbia University in July 2025, Dr. Zhou earned her Ph.D. in Machine Learning from Georgia Institute of Technology.