Moulinath Banerjee

Moulinath Banerjee is a Professor of Statistics at the University of Michigan, affiliated with the Department of Statistics within the College of Literature, Science, and the Arts (LSA). He holds a B.Stat and M.Stat from the Indian Statistical Institute and a Ph.D. from the University of Washington. His research focuses on non-standard statistical problems, empirical process theory, threshold estimation, graphical networks, and the intersection of statistics with machine learning, particularly in distributed computing and data integration.

Education:

• B.Stat (Hons), Indian Statistical Institute, 1995
• M.Stat (Mathematical Statistics and Probability), Indian Statistical Institute, 1997
• Ph.D. in Statistics, University of Washington, 2000

Research Interests:

• Inference under shape-restrictions and non-differentiable models
• Statistics-ML interface, including transfer learning and weak supervision
• High-dimensional and low-dimensional statistical methods
• Applications in crime modeling, policy evaluation, and causal inference

Recent work emphasizes statistical methodologies for modern challenges like distributed computing, data integration, and performativity in predictive systems. His articles span topics such as change-plane regression, Hawkes processes, and posterior drift in transfer learning, reflecting contributions to both theory and applied domains.

Scientific Awards:

• 2011 IISA Young Investigators Award
• Fellow of the Institute of Mathematical Statistics (IMS)
• Fellow of the American Statistical Association (ASA)
• IMS Medallion Lecture Awardee (2024)

Teaching includes advanced courses in statistical theory (e.g., Stats 610, 611, 612) and applied methods (e.g., Stats 412, 425). Collaborations span academia and industry, addressing interdisciplinary challenges in data science and statistical methodology.