Frederik Kunstner

SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient

Aaron Mishkin, Frederik Kunstner, Didrik Nielsen, 2018, NeurIPS.

Adaptive Gradient Methods Converge Faster with Over-Parameterization (and you can do a line-search) pdf

Frederik Kunstner, Sharan Vaswani, Issam Laradji, 2020, ArXiv.

Limitations of the Empirical Fisher Approximation pdf

Frederik Kunstner, Philipp Hennig, Lukas Balles, 2019, NeurIPS.

Limitations of the empirical Fisher approximation for natural gradient descent

Frederik Kunstner, Philipp Hennig, Lukas Balles, 2019, NeurIPS.

BackPACK: Packing more into backprop pdf

Frederik Kunstner, Philipp Hennig, Felix Dangel, 2020, ICLR.

Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent pdf

Frederik Kunstner, Raunak Kumar, Mark Schmidt, 2020, ArXiv.

Adaptive Gradient Methods Converge Faster with Over-Parameterization (and you can do a line-search) pdf

Frederik Kunstner, Mark W. Schmidt, Issam H. Laradji, 2020, ArXiv.