I’m a PhD student at UBC working with Mark Schmidt.
I am interested in algorithms and optimization methods for machine learning applications.

Before coming to UBC, I did my BSc and MSc at EPFL.
I interned at the MPI working with Philipp Hennig and at RIKEN working with Emtiyaz Khan.


Papers

Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent
F. Kunstner, R. Kumar, M. Schmidt. AISTATS 2021 [arXiv, .bib]

BackPACK: Packing more into backprop
F. Dangel, F. Kunstner, P. Hennig. ICLR 2020 [arXiv, code, website, .bib]

Limitations of the empirical Fisher approximation
F. Kunstner, L. Balles, P. Hennig. Neurips 2019 [arXiv, .bib]

SLANG: fast structured covariance approximations for Bayesian deep learning with natural gradient
A. Mishkin, F. Kunstner, D. Nielsen, M. Schmidt, M.E. Khan. Neurips 2018 [arXiv, .bib]


Software utilities

Tex2UTF8: quick and dirty LaTeX to UTF8 converter
DSDL: Dataset downloader library for libsvm datasets