Follow
Lukas Balles
Lukas Balles
Amazon Research
Verified email at amazon.com - Homepage
Title
Cited by
Cited by
Year
Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation
A Ranjan, V Jampani, L Balles, K Kim, D Sun, J Wulff, MJ Black
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2019
3692019
Coupling Adaptive Batch Sizes with Learning Rates
L Balles, J Romero, P Hennig
Proceedings of the Thirty-Third Conference on Uncertainty in Artificial …, 2017
972017
Limitations of the empirical fisher approximation for natural gradient descent
F Kunstner, P Hennig, L Balles
Advances in neural information processing systems 32, 2019
932019
Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients
L Balles, P Hennig
Proceedings of the 35th International Conference on Machine Learning (ICML …, 2018
812018
Early stopping without a validation set
M Mahsereci, L Balles, C Lassner, P Hennig
arXiv preprint arXiv:1703.09580, 2017
582017
DeepOBS: A Deep Learning Optimizer Benchmark Suite
F Schneider, L Balles, P Hennig
Seventh International Conference on Learning Representations (ICLR), 2019
292019
The Geometry of Sign Gradient Descent
L Balles, F Pedregosa, N Le Roux
arXiv preprint arXiv:2002.08056, 2020
62020
Self-tuning stochastic optimization with curvature-aware gradient filtering
RTQ Chen, D Choi, L Balles, D Duvenaud, P Hennig
PMLR, 2020
42020
Automating stochastic optimization with gradient variance estimates
L Balles, M Mahsereci, P Hennig
ICML AutoML Workshop, 13, 2017
32017
Gradient-Matching Coresets for Rehearsal-Based Continual Learning
L Balles, G Zappella, C Archambeau
arXiv preprint arXiv:2203.14544, 2022
2022
Gradient-matching coresets for continual learning
L Balles, G Zappella, C Archambeau
arXiv preprint arXiv:2112.05025, 2021
2021
The system can't perform the operation now. Try again later.
Articles 1–11