Wednesday, October 21, 2020 - 4:00pm to 4:30pm
Event Calendar Category
LIDS & Stats Tea
Zoom meeting id
935 8803 7348
Join Zoom meeting
Low-rank approximation of the Gaussian kernel is a core component of many data-science algorithms. Often the approximation is desired over an algebraic variety (e.g., in problems involving sparse data or low-rank data). Can better approximations be obtained in this setting? In this talk, I’ll show that the answer is yes: The improvement is exponential and controlled by the variety’s Hilbert dimension.
Joint work with Pablo Parrilo
Jason is a PhD student in LIDS, advised by Pablo Parrilo. His research interests are in large-scale convex optimization, with a recent focus on scalable algorithms for optimal transport and related problems.