Lukas Balles
Lukas Balles
Amazon Research
Bestätigte E-Mail-Adresse bei - Startseite
Zitiert von
Zitiert von
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
Coupling Adaptive Batch Sizes with Learning Rates
L Balles, J Romero, P Hennig
Proceedings of the Thirty-Third Conference on Uncertainty in Artificial …, 2017
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
Limitations of the empirical fisher approximation for natural gradient descent
F Kunstner, L Balles, P Hennig
arXiv preprint arXiv:1905.12558, 2019
Early stopping without a validation set
M Mahsereci, L Balles, C Lassner, P Hennig
arXiv preprint arXiv:1703.09580, 2017
DeepOBS: A Deep Learning Optimizer Benchmark Suite
F Schneider, L Balles, P Hennig
Seventh International Conference on Learning Representations (ICLR), 2019
Automating stochastic optimization with gradient variance estimates
L Balles, M Mahsereci, P Hennig
ICML AutoML Workshop, 13, 2017
Self-Tuning Stochastic Optimization with Curvature-Aware Gradient Filtering
RTQ Chen, D Choi, L Balles, D Duvenaud, P Hennig
arXiv preprint arXiv:2011.04803, 2020
The Geometry of Sign Gradient Descent
L Balles, F Pedregosa, NL Roux
arXiv preprint arXiv:2002.08056, 2020
Limitations of the empirical Fisher approximation for natural gradient descent
L Balles
Deep Learning for Diabetic Retinopathy Diagnostic
L Balles
Universität Heidelberg Heidelberg, 2016
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–11