Melanie Weber

Melanie Weber

Assistant Professor

Harvard University


I am an Assistant Professor of Applied Mathematics and of Computer Science at Harvard, where I lead the Geometric Machine Learning Group. My research focuses on utilizing geometric structure in data for the design of efficient Machine Learning and Optimization methods with provable guarantees.

In 2021-2022, I was a Hooke Research Fellow at the Mathematical Institute in Oxford and a Nicolas Kurti Junior Research Fellow at Brasenose College. In Fall 2021, I was a Research Fellow at the Simons Institute in Berkeley, where I participated in the program Geometric Methods for Optimization and Sampling. Previously, I received my PhD from Princeton University (2021) under the supervision of Charles Fefferman, held visiting positions at MIT and the Max Planck Institute for Mathematics in the Sciences and interned in the research labs of Facebook, Google and Microsoft.

My research is supported by the National Science Foundation, the Sloan Foundation and the Harvard Data Science Initiative.

  • Data Geometry
  • Graph Machine Learning
  • Optimization on Manifolds
  • Machine Learning in Non-Euclidean spaces
  • Label- and Resource-efficient Learning
  • PhD in Applied Mathematics, 2021

    Princeton University

  • BSc/MSc in Mathematics and Physics, 2016

    University of Leipzig

  • MSc in Applied Mathematics (during year abroad), 2015

    University of Washington

Recent Publications

Quickly discover relevant content by filtering publications.
(2024). Hardness of Learning Neural Networks under the Manifold Hypothesis. Under Review.

PDF Project

(2024). Contrastive Poincaré Maps for single-cell data analysis. ICLR MLGenX.

PDF Project

(2024). On the Hardness of Learning under Symmetries. ICLR (spotlight).

PDF Project


Discrete Curvature and Machine Learning on Graphs
Discrete Ricci curvature for curvature-based analysis of complex networks.
Optimization on Manifolds
Exploiting geometric structure in (non)convex (constrained) optimization.
Learning to Control with Little Data
Provable, adaptive strategies for agnostic control.
Machine Learning in Non-Euclidean Spaces
Harnessing the geometric structure of data in Machine Learning.

Upcoming and Recent Talks


  • Office hours by appointment. If you are a Harvard undergraduate or graduate student interested in working with me, please send me an email. Due to high email volume, I am unable to reply to most emails from non-Harvard students regarding admission, supervised projects or internships.