Eddie Cunningham

PhD Candidate, UMass Amherst

prof_pic.jpg

My research sits at the intersection of differential geometry, generative modeling, and representation learning. I am interested in characterizing the geometric structure of data in order to understand how to build better representations of data and interpretable generative models. My other research interests include diffusion based time series modeling and sampling using normalizing flows or stochastic optimal control based methods.

selected publications

  1. ICML
    principal-component-flows.png
    Principal Component Flows
    Edmond Cunningham, Adam D. Cobb, and Susmit Jha
    In Proceedings of the 39th International Conference on Machine Learning, 2022
  2. AISTATS
    change-of-variables-rectangular.png
    A Change of Variables Method For Rectangular Matrix-Vector Products
    Edmond Cunningham and Madalina Fiterau
    In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021