EPFL Papers at ICLR 2020
EPFL researchers will be presenting the following 12 papers at ICLR, the International Conference on Learning Representations, held in Addis Ababa, Ethiopia coming April 2020. While this is the 8th instance of the conference, it is the first major machine learning research conference to be hosted on the African continent!
If you are attending ICLR 2020, we hope to meet and discuss!
List of Accepted EPFL Papers:
- Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
Shell Xu Hu, Pablo Moreno, Yang Xiao, Xi Shen, Guillaume Obozinski, Neil Lawrence, Andreas Damianou - Tensor Decompositions for Temporal Knowledge Base Completion
Timothée Lacroix, Guillaume Obozinski, Nicolas Usunier - Evaluating The Search Phase of Neural Architecture Search
Kaicheng Yu, Christian Sciuto, Martin Jaggi, Claudiu Musat, Mathieu Salzmann - DeepSphere: a graph-based spherical CNN
Michaël Defferrard, Martino Milani, Frédérick Gusset, Nathanaël Perraudin - Don't Use Large Mini-batches, Use Local SGD
Tao Lin, Sebastian U. Stich, Kumar Kshitij Patel, Martin Jaggi - Dynamic Model Pruning with Feedback
Tao Lin, Sebastian U. Stich, Luis Barba, Daniil Dmitriev, Martin Jaggi - What graph neural networks cannot learn: depth vs width
Andreas Loukas - The asymptotic spectrum of the Hessian of DNN throughout training
Arthur Jacot, Franck Gabriel, Clement Hongler - Lipschitz constant estimation for Neural Networks via sparse polynomial optimization
Fabian Latorre, Paul Rolland, Volkan Cevher - Decentralized Deep Learning with Arbitrary Communication Compression
Anastasia Koloskova*, Tao Lin*, Sebastian U Stich, Martin Jaggi - On the Relationship between Self-Attention and Convolutional Layers
Jean-Baptiste Cordonnier, Andreas Loukas, Martin Jaggi - Domain Adaptive Multiflow Networks
Róger Bermúdez-Chacón, Mathieu Salzmann, Pascal Fua
image by recommend.com