Jonas Kohler
Jonas Kohler
Verified email at - Homepage
Cited by
Cited by
Sub-sampled cubic regularization for non-convex optimization
JM Kohler, A Lucchi
International Conference on Machine Learning (ICML) 2017, 2017
Escaping Saddles with Stochastic Gradients
H Daneshmand, J Kohler, A Lucchi, T Hofmann
International Conference on Machine Learning (ICML) 2018, 2018
Exponential convergence rates for Batch Normalization: The power of length-direction decoupling in non-convex optimization
J Kohler, H Daneshmand, A Lucchi, M Zhou, K Neymeyr, T Hofmann
International Conference on Artificial Intelligence and Statistics (AISTATS …, 2019
A Stochastic Tensor Method for Non-convex Optimization
A Lucchi, J Kohler
arXiv preprint arXiv:1911.10367, 2019
The Role of Memory in Stochastic Optimization
A Orvieto, J Kohler, A Lucchi
UAI, 2019, 2019
Adaptive norms for deep learning with regularised Newton methods
J Kohler, L Adolphs, A Lucchi
NeurIPS 2019 Workshop: Beyond First-Order Optimization Methods in Machine …, 2019
Batch normalization provably avoids ranks collapse for randomly initialised deep networks
H Daneshmand, J Kohler, F Bach, T Hofmann, A Lucchi
Neural Information Processing Systems (NeurIPS 2020), 2020
Two-Level K-FAC Preconditioning for Deep Learning
N Tselepidis, J Kohler, A Orvieto
NeurIPS 2020 Workshop on Optimization for Machine Learning (OPT2020), 2020
The system can't perform the operation now. Try again later.
Articles 1–8