Florian Schäfer

prof_pic.jpg

S1317 CODA

756 W Peachtree St

Atlanta, GA 30332

I’m Florian Schäfer, assistant professor in the School of Computational Science and Engineering at Georgia Tech.

Prior to joining Georgia Tech, I received my PhD in applied and computational mathematics at Caltech, working with Houman Owhadi. Before that, I received my Bachelor’s and Master’s degrees in Mathematics at the University of Bonn.

My research interests lie at the interface of numerical computation, statistical inference, and competitive games. To learn more, have a look at these high-level summaries or the defense of my thesis.

I am currently hiring PhD students. If you have a strong background in computational mathematics and the above seems interesting (or you have a project in mind that I might find interesting), feel free to reach out!

news

Feb 4, 2023 Paper on variational inference with double KL minimization now on the arXiv! First authors are Jian Cao and Myeongjong Kang from the group of Matthias Katzfuss.
Jan 20, 2023 Congratulations to Qi Zeng, for getting his paper on Competitive Physics-Informed Networks accepted at ICLR 2023! Joint work with Yash Kothari and Spencer Bryngelson.
Jan 20, 2023 I am giving an invited plenary talk at the Georgia Scientific Computing Symposium (GSCS 2023) on Saturday February 18.
Dec 21, 2022 New version of our paper on the recovery of elliptic solvers from matrix-vector products now on the arXiv. With greatly extended experiments, plenty of new figures, and theoretical results on the recovery of the continuous Green’s function. Joint work with Houman.
Nov 30, 2022 Congratulations to Jiawei for having his paper on ZerO Initialization for deep neural networks accepted at TMLR!

selected publications

  1. Sparse Cholesky factorization by Kullback-Leibler minimization
    Florian Schäfer, Matthias Katzfuss, and Houman Owhadi
    SIAM Journal on Scientific Computing 2021
    arXiv
  2. Compression, inversion, and approximate PCA of dense kernel matrices at near-linear computational complexity
    Florian Schäfer, T. J. Sullivan, and Houman Owhadi
    Multiscale Model. Simul. 2021
    arXiv Blog
  3. Implicit competitive regularization in GANs
    Florian Schäfer, Hongkai Zheng, and Anima Anandkumar
    In the 37th International Conference on Machine Learning (ICML 2020) 2021
    arXiv Blog Slides
  4. Competitive Gradient Descent
    Florian Schäfer, and Anima Anandkumar
    In Advances in Neural Information Processing Systems 32 2021
    arXiv HTML Blog
  5. Sparse recovery of elliptic solvers from matrix-vector products
    Florian Schäfer, and Houman Owhadi
    arXiv preprint arXiv:2110.05351 2022
    arXiv