In October 2025, a paper on variational inference for uncertainty quantification was accepted to JMLR; in September 2025, two papers on variational inference with Feynman parameterizations and benchmarks for cosmological data analysis were accepted to NeurIPS; in May 2025, received the best paper award at AI-STATS conference; in March 2025, won the Flywire VNC Matching Challenge.
Research Experience
Currently working at the Center for Computational Mathematics (CCM) at the Flatiron Institute, involved in machine learning research. Previously, he was a tenured faculty member at UC San Diego and UPenn, and a member of the technical staff at AT&T Labs.
Education
Bachelor's degree in Physics from Harvard and a doctorate in Physics from M.I.T.
Background
Senior Research Scientist, focusing on high-dimensional data analysis, latent variable modeling, variational inference, and representation learning. Previously, he was a tenured faculty member at UC San Diego and UPenn, and a member of the technical staff at AT&T Labs. He also served as Editor-in-Chief of the Journal of Machine Learning Research and as Program Chair of the Conference on Neural Information Processing Systems.
Miscellany
Will be speaking at the Workshop on the Physics of John Hopfield: Learning and Intelligence at Princeton, the Workshop on Low-Rank Models and Applications at the University of Mons, and the Workshop on Geometric and Combinatorial Methods in the Foundations of CS and AI at Oxford.