Подписаться
Frederik Kunstner
Frederik Kunstner
University of British Columbia
Подтвержден адрес электронной почты в домене cs.ubc.ca - Главная страница
Название
Процитировано
Процитировано
Год
Limitations of the empirical Fisher approximation for natural gradient descent
F Kunstner, L Balles, P Hennig
Advances in Neural Information Processing Systems 32, 4158--4169, 2019
1632019
BackPACK: Packing more into Backprop
F Dangel, F Kunstner, P Hennig
International Conference on Learning Representations, 2020
912020
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 31, 6248--6258, 2018
622018
Adaptive gradient methods converge faster with over-parameterization (but you should do a line-search)
S Vaswani, I Laradji, F Kunstner, SY Meng, M Schmidt, S Lacoste-Julien
arXiv preprint arXiv:2006.06835, 2020
27*2020
Homeomorphic-Invariance of EM: Non-Asymptotic Convergence in KL Divergence for Exponential Families via Mirror Descent
F Kunstner, R Kumar, M Schmidt
International Conference on Artificial Intelligence and Statistics 130, 3295 …, 2021
222021
Noise is not the main factor behind the gap between sgd and adam on transformers, but sign descent might be
F Kunstner, J Chen, JW Lavington, M Schmidt
arXiv preprint arXiv:2304.13960, 2023
112023
Fully Quantized Distributed Gradient Descent
F Künstner, SU Stich, M Jaggi
Technical report, EPFL, 2017
82017
Convergence Rates for the MAP of an Exponential Family and Stochastic Mirror Descent--an Open Problem
RL Priol, F Kunstner, D Scieur, S Lacoste-Julien
arXiv preprint arXiv:2111.06826, 2021
12021
Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking
F Kunstner, VS Portella, M Schmidt, N Harvey
arXiv preprint arXiv:2306.02527, 2023
2023
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–9