Statistics for
structured data
High-dimensional estimation, topic models, and data integration that account for sparsity, networks, and spatial relationships.
Statistics · Machine Learning · Biology
Claire Donnat
Assistant Professor of Statistics
University of Chicago
I develop statistical and machine-learning methods for high-dimensional data with group, spatial, or network structure.
My work connects statistical theory with questions in biology—from spatial gene expression to the organization of microbial communities. I lead the SIGNAL Lab at UChicago.
Research directions
Explore my researchStatistics for
Understanding
learning on graphs
Statistical foundations for graph neural networks: how they learn, when they work, and how to quantify their uncertainty.
Methods for
biological discovery
Statistical tools for spatial transcriptomics, plant and microbial systems, and the relationships between genes and traits.
My research group
The SIGNAL Lab
Meet the people behind the research, explore our projects and software, and follow the latest from the group.
Selected recent work
All publicationsCanonical Correlation Analysis as Reduced Rank Regression in High Dimensions
Claire Donnat and Elena Tuzhilina
SpeedCP: Fast Kernel-based Conditional Conformal Prediction
Yating Liu, Yeo Jin Jung, Zixuan Wu, So Won Jeong, and Claire Donnat
Tensor Topic Modeling via HOSVD
Yating Liu and Claire Donnat
Background
I received my Ph.D. in Statistics from Stanford University in 2020, advised by Susan Holmes and jointly working with Jure Leskovec, after studying applied mathematics at École Polytechnique. I joined UChicago in 2020 and received an NSF CAREER Award in 2023.
Education & experienceContact & consulting
For research collaborations or consulting in statistical methodology, graph-based modeling, and data integration for the life sciences, contact me by email.
cdonnat@uchicago.eduThe lab is not currently accepting applications.