I am a Hooke Research Fellow at the Mathematical Institute at the University of Oxford and a Nicolas Kurti Junior Research Fellow at Brasenose College. In Fall 2021, I will be a Research Fellow at the Simons Institute for the Theory of Computing, participating in the special program on Geometric Methods in Optimization and Sampling.
My research focuses on understanding the geometric features of data mathematically and on developing machine learning methods that utilize this knowledge. This includes in particular:
Geometric Methods for Optimization and Machine Learning (read more here: ML in Non-Euclidean Spaces, Riemannian Optimization and Discrete Geometry and Network Analysis);
Mathematical Learning and Control Theory (read more).
I recieved my PhD from Princeton University in 2021, where I was very fortunate to be advised by Charles Fefferman. I have also spent time at MIT’s Laboratory for Information and Decision Systems, the Max Planck Institute for Mathematics in the Sciences, as well as at the research labs of Facebook (FAIR), Google and Microsoft.
View my current CV here.
PhD in Applied Mathematics, 2021
Princeton University
BSc/MSc: Mathematics + Physics, 2016
University of Leipzig
MSc in Applied Math, 2015
University of Washington
May 20, 2021, SIAM Conference on Applied Linear Algebra (Minisymposium: Linear Algebra and Differential Geometry)
Jan 20, 2021, One World Seminar Series: Mathematics of Machine Learning
Jan 5, 2021, Joint Mathematics Meeting (AMS Special Session: Geometry in the Mathematics of Data Science)
Dec 11, 2020, NeurIPS Workshop Differential Geometry meets Deep Learning
Learning in the sparse data regime.
Nonconvex and g-convex optimization on manifolds.
Forman-Ricci curvature and discrete geometric flows for a curvature-based analysis of complex networks.
Understanding and Learning the Geometry of Data.