Aaron Mishkin
Aaron Mishkin
Verified email at cs.ubc.ca - Homepage
Cited by
Cited by
Painless stochastic gradient: Interpolation, line-search, and convergence rates
S Vaswani, A Mishkin, I Laradji, M Schmidt, G Gidel, S Lacoste-Julien
Advances in Neural Information Processing Systems, 3732-3745, 2019
Slang: Fast structured covariance approximations for bayesian deep learning with natural gradient
A Mishkin, F Kunstner, D Nielsen, M Schmidt, ME Khan
Advances in Neural Information Processing Systems, 6245-6255, 2018
To Each Optimizer a Norm, To Each Norm its Generalization
S Vaswani, R Babanezhad, J Gallego, A Mishkin, S Lacoste-Julien, ...
arXiv preprint arXiv:2006.06821, 2020
The system can't perform the operation now. Try again later.
Articles 1–3