Aaron Mishkin

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

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

To Each Optimizer a Norm, To Each Norm its Generalization pdf

Aaron Mishkin, Nicolas Le Roux, Reza Babanezhad, 2020, ArXiv.

Painless Stochastic Gradient: Interpolation, Line-Search, and Convergence Rates

Aaron Mishkin, Mark W. Schmidt, Issam H. Laradji, 2019, NeurIPS.