Claire Donnat (UChicago): AI+ Science Schmidt Fellows Speaker Series
Organized by the University of Chicago’s Eric and Wendy Schmidt AI in Science Postdoctoral Fellowship Program.
Agenda
4:00pm – 4:45pm: Presentation
4:45pm – 5:00pm: Q&A
5:00pm – 5:30pm: Reception
Meeting location
William Eckhardt Research Center. Room 401
5640 S Ellis Avenue, Chicago, IL 60637
Map It
Abstract: Topic modeling uncovers latent structures in text and count data by representing data points as mixtures of topics. Incorporating sample-level information can improve estimation, but Bayesian approaches often lack theoretical guarantees and are computationally expensive. We propose two frequentist extensions of probabilistic latent semantic indexing (pLSI). The first models document similarities as a graph, using a fast graph-regularized SVD estimator to enforce topic consistency. The second adapts pLSI for data with natural tensor structure. We establish high-probability bounds on estimation error and validate our methods on synthetic and real-world datasets, demonstrating improved topic inference.
Bio: Claire Donnat, Assistant Professor, Department of Statistics, University of Chicago. I completed my PhD in Statistics in June 2020 at Stanford University, where I was lucky to be supervised by Professor Susan Holmes and where I had the chance to work with Prof. Jure Leskovec. Prior to Stanford, I studied Applied Mathematics and Engineering at Ecole Polytechnique (France), where I received an M.S and B.S equivalent.
My research interests lie in the analysis of patterns and the quantification of uncertainty in high-dimensional datasets, and in particular, graphs and networks, geared towards biomedical applications.
Parking
Campus North Parking
5505 S Ellis Ave
Map It

Yuan-Sen Ting (OSU): AI+Science Schmidt Fellows Speaker Series

Shirley Ho (Flatiron Institute): AI+ Science Schmidt Fellows Speaker Series

Chibueze Amanchukwu (UChicago): AI+ Science Schmidt Fellows Speaker Series
