CARE-AI Seminar Series Featuring Dr. Geoff Pleiss

Seminar Title: Ensembles in the Age of Overparameterization: Promises and Pathologies

The CARE-AI seminar series at the University of Guelph welcomes Dr. Geoff Pleiss, Assistant Professor, in the Department of Statistics at The University of British Columbia as well as a Canada CIFAR AI Chair affiliated with the Vector Institute. Geoff’s research group specializes in uncertainty quantification in machine learning, especially within the contexts of decision making, optimal experimental design, and scientific discovery. His most notable research contributions include work on neural network calibration, scalable Gaussian processes, and ensemble methods. Additionally, Geoff has co-founded many widely-used open source software projects, including the GPyTorch, LinearOperator, and CoLA libraries.