I am a PhD student at Princeton University, where I am very fortunate to be advised by Charles Fefferman. My research interests include Geometric Representations of Data and Theoretical Machine Learning. This includes in particular:
understanding the geometric nature of data and how to exploit geometric concepts in machine learning and data mining;
developing a mathematical understanding of how much we can learn about a function and how to determine sample complexities and choices for different classes of learning problems.
Furthermore, I am interested in Discrete Geometry and Machine Learning on Graphs; specifically in methods that use discrete notions of curvature (read more).
I spent summer 2017 at MIT working with Suvrit Sra at LIDS. In summer 2018 I interned at Facebook Research (FAIR) in NYC, where I worked with Max Nickel.
View my current CV here.
PhD in Applied Mathematics, 2021
Princeton University
Undergraduate: Mathematics + Physics, 2016
University of Leipzig
Aug 28, 2018, NYC Machine Learning and Artificial Intelligence Meetup
May 15, 2018, Bridging Mathematical Optimization, Information Theory and Data Science
Apr 4, 2018, Seminar, Max Planck Institute for Mathematics in the Sciences
Mar 28, 2018, EPFL Applied Topology Seminar
Feb 3, 2018, New Deep Learning Techniques
Forman-Ricci curvature and discrete geometric flows for a curvature-based analysis of complex networks.
Convolutional Neural Networks for Event Classification at LHC’s ATLAS experiment.
Efficient tools for functional characterization of gene networks.
Understanding and Learning the Geometry of Data.
Neural networks model for effects of brain disorders on associative memory.