

Deep Learning Theory Kickoff Meeting
Program
All talks will be held in room E1 05 (Leibniz-Saal),
Max Planck Institute for Mathematics in the Sciences (Leipzig, Inselstr. 22).
Wednesday, March 27, 2019 | ||
---|---|---|
08:30 - 09:00 | Registration / Coffee & Tee | |
09:00 - 09:15 | Welcome Address (Bernd Sturmfels) | |
09:15 - 09:45 | Guido Montúfar (Max Planck Institute for Mathematics in the Sciences) Introduction Deep Learning Theory | |
09:45 - 10:00 | Coffee & Tee | |
10:00 - 11:00 | Nihat Ay (Max Planck Institute for Mathematics in the Sciences) On the Natural Gradient for Deep Learning | |
11:00 - 12:00 | Tim Genewein (DeepMind London) Neural Network Compression - model-capacity and parameter redundancy of neural networks | |
12:00 - 13:00 | Lunch Buffet at the Institute | |
13:00 - 14:00 | Ingo Steinwart (Universität Stuttgart) A Sober Look at Neural Network Initializations | |
14:00 - 15:00 | Grégoire Montavon (Machine Learning, Technische Universität Berlin) Explaining the Decisions of Deep Neural Networks | |
15:00 - 15:30 | Coffee & Tee | |
15:30 - 16:30 | Frederik Künstner (École Polytechnique Fédérale de Lausanne) Limitations of the Empirical Fisher Approximation | |
16:30 - 18:00 | Poster Session & Coffee & Tee | |
18:00 - 18:30 | Discussions | |
19:00 | Dinner (together in Thueringer Hof, Burgstraße 19, 04109 Leipzig), departure from MPI main entrance at 18:30, 20 min walk | |
Thursday, March 28, 2019 | ||
09:00 - 10:00 | Coffee & Tee | |
10:00 - 11:00 | Razvan Pascanu (DeepMind London) Looking at data efficiency in RL | |
11:00 - 12:00 | Maurice Weiler (Machine Learning Lab, University of Amsterdam) Gauge Equivariant Convolutional Networks | |
12:00 - 13:00 | Lunch Buffet at the Institute | |
13:00 - 14:00 | Johannes Rauh (Max Planck Institute for Mathematics in the Sciences) Synergy, redundancy and unique information | |
14:00 - 15:00 | Michael Arbel (Gatsby Computational Neuroscience Unit, University College London) Kernel Distances for Deep Generative Models | |
15:00 - 16:00 | Poster Session & Coffee & Tee | |
16:00 - 17:00 | Yonatan Dukler (UCLA, Department of Mathematics) Wasserstein of Wasserstein Loss for Learning Generative Models | |
17:00 - 18:00 | Poster Session & Coffee & Tee | |
19:00 | Dinner (individually) | |
Friday, March 29, 2019 | ||
09:00 - 10:00 | Coffee & Tee | |
10:00 - 11:00 | Nico Scherf (Max Planck Institute for Human Cognitive and Brain Sciences) On Open Problems for Deep Learning in Biomedical Image Analysis | |
11:00 - 12:00 | Wuchen Li (UCLA, Department of Mathematics) Wasserstein Information Geometry | |
12:00 - 13:00 | Lunch Buffet at the Institute | |
13:00 - 14:00 | Eliana Duarte (Max Planck Institute for Mathematics in the Sciences) Discrete Statistical Models with Rational Maximum Likelihood Estimator | |
14:00 - 15:00 | Pradeep Banerjee (Max Planck Institute for Mathematics in the Sciences) The Blackwell Information Bottleneck | |
15:00 - 15:30 | Coffee & Tee | |
15:30 - 16:30 | Luigi Malagò (Romanian Institute of Science and Technology - RIST, Cluj-Napoca) On the Information Geometry of Word Embeddings | |
16:30 - 17:00 | Concluding Remarks |
Date and Location
March 27 - 29, 2019
Max Planck Institute for Mathematics in the Sciences
Inselstr. 22
04103 Leipzig
Scientific Organizers
Guido Montúfar
MPI for Mathematics in the Sciences
Administrative Contact
Valeria HünnigerMPI für Mathematik in den Naturwissenschaften