Jason M. Klusowski is an Assistant Professor in the Department of Operations Research & Financial Engineering (ORFE) at Princeton University, where he is also a Participating Faculty in the Center for Statistics and Machine Learning (CSML). His research interests broadly span statistical machine learning for complex, large-scale models, focusing on the trade-offs between interpretability, statistical accuracy, and computational feasibility. He works on topics such as decision trees and ensemble learning (CART, random forests, stacking), neural networks (approximation theory and statistical properties), gradient-based optimization (ADAM, SGD), and the large limit behavior of statistical models (Lasso, Slope). Recently, his research has expanded to include the study of transformers and large language models.

Prior to joining Princeton, Jason was an Assistant Professor in the Department of Statistics at Rutgers University, New Brunswick. He completed his Ph.D. in Statistics and Data Science at Yale University in 2018 under the supervision of Andrew R. Barron. From 2017 to 2018, he was a visiting graduate student in the Statistics Department at The Wharton School, University of Pennsylvania.

Jason currently serves on the editorial board of Bernoulli—Journal of the Bernoulli Society. His research is partially supported by a Sloan Research Fellowship in Mathematics and NSF CAREER DMS-2239448, and previously by NSF DMS-2054808 and TRIPODS DATA-INSPIRE Institute CCF-1934924.

Jason grew up in the heart of the Canadian Prairies, in the city of Winnipeg. His spouse is an Assistant Professor of Marketing at Yale University.

• February 2025. I am looking for a postdoctoral research associate to start June 1st. Please apply here.
• February 2025. I received a Sloan Research Fellowship in Mathematics.
• January 2025. Paper on decoding strategies for neural sequence models with Sijin Chen and Omar Hagrass to appear in ICLR.
• November 2024. Paper on sharp convergence rates for matching pursuit with Jonathan Siegel to appear in IEEE Transactions on Information Theory.
• November 2024. New paper on statistical-computational trade-offs for recursive adaptive partitioning estimators with Yan Shuo Tan and Krishnakumar Balasubramanian.
• September 2024. Starting January 2025, I will be an associate editor for Bernoulli.
• September 2024. Two new papers on transformers to appear in NeurIPS: (1) global convergence in training large-scale transformers and (2) one-layer transformer provably learns one-nearest neighbor in context, with Cheng Gao, Yuan Cao, Zihao Li, Yihan He, Mengdi Wang, Han Liu, and Jianqing Fan.
• May 2024. Paper on the implicit bias of Adam with Matias Cattaneo and Boris Shigida to appear in ICML.