Michael J. Catanzaro

Senior Scientist, Geometric Data Analytics, Inc.

mike.jpg

Hello!

I am a mathematician turned data scientist interested in solving problems in big data and machine learning. Lately I’ve been working on simplifying machine learning problems using the tools of algebraic topology. Before this, I studied topological data analysis and its applications on a variety of applied problems, ranging from understanding deep perception models to analyzing fMRI data. Once upon a time, I studied stochastic topology and empirical currents as they arise in physics and statistical mechanics.

I am currently a Senior Scientist at Geometric Data Analytics, Inc. Prior to this, I was an Assistant Professor in the mathematics department at Iowa State University, a postdoc at the Unviersity of Florida, and a graduate student at Wayne State University. I earned my PhD in 2016 under the supervision of John Klein and Vladimir Chernyak and was mentored by Peter Bubenik as a postdoc.

I like to do lots of other things besides math, machine learning, and physics.

selected publications

  1. swot_preview.png
    Deep Learning Methods for Inference of Sea Surface Kinematics from SWOT Altimetry
    James B. Polly, Kenneth Ball, Michael Catanzaro, and Jay Hineman
    OCEANS 2024 - Halifax, 2024
  2. frontiers_preview.png
    Implications of Data Topology for Deep Generative Models
    Jin Yinzhu, Rory McDaniel, Joseph N. Tatro, Michael J. CatanzaroAbraham D. SmithPaul Bendich, Matthew B. Dwyer, and P. Thomas Fletcher
    Frontiers in Computer Science, 2024
  3. parallax_preview.png
    Topological Parallax: A Geometric Specification for Deep Perception Models
    Abraham SmithMichael Catanzaro, Gabrielle Angeloro, Nirav Patel, and Paul Bendich
    In Advances in Neural Information Processing Systems , 2023