

Conference on Mathematics of Machine Learning
Program
All talks will be held in room Plenarsaal,
Center for Interdisciplinary Research (ZiF), Bielefeld University (Bielefeld, Methoden 1) and broadcasted via Zoom.
Wednesday, August 04, 2021 | ||
---|---|---|
10:00 - 10:30 | Welcome | |
10:30 - 11:00 | Coffee Break | |
11:00 - 12:00 | Lenka Zdeborová (EPFL - École Polytechnique Fédérale de Lausanne, Switzerland) Understand machine learning via exactly solvable statistical physics models | |
12:00 - 12:30 | Youness Boutaib (RWTH Aachen University, Germany) Path classification by stochastic linear RNNs | |
12:30 - 13:00 | Yuguang Wang (Max Planck Institute for Mathematics in the Sciences (Leipzig), Germany) How framelets enhance graph neural networks | |
13:00 - 14:00 | Lunch Break | |
14:00 - 14:30 | Luca Ratti (University of Genoa (Genova), Italy) Learning the optimal regularizer for linear inverse problems | |
14:30 - 15:00 | Florent Krzakala (EPFL (Lausanne), Switzerland) Generalization & Overparametrization in Machine Learning: Rigorous Insights from Simple Models | |
15:00 - 15:30 | Coffee Break | |
15:30 - 16:00 | Oxana Manita (Eindhoven University of Technology, Netherlands) Dropout regularization viewed from the large deviations perspective | |
16:00 - 16:30 | Jochen Merker (HTWK Leipzig, Germany) Complexity-reduced data models beyond the classical bias-variance trade-off | |
16:30 - 17:00 | Coffee Break | |
17:00 - 18:00 | Peter Bartlett (University of California, Berkeley, USA) Benign overfitting | |
18:00 - 19:00 | Stefano Soatto (University of California, Los Angeles, USA) The Information in Optimal Representations | |
19:00 | Dinner @ ZIF | |
Thursday, August 05, 2021 | ||
09:30 - 10:30 | Ingo Steinwart (University of Stuttgart, Germany) to be announced | |
10:30 - 11:00 | Coffee Break | |
11:00 - 12:00 | Dmitry Yarotsky (Skoltech, Russia) Universal scaling laws in the gradient descent training of neural networks | |
12:00 - 12:30 | Andreas Habring (University of Graz, Austria) A Generative Variational Model for Inverse Problems in Imaging | |
12:30 - 14:00 | Lunch Break | |
14:00 - 15:00 | Poster Session | |
15:00 - 15:30 | Coffee Break | |
15:30 - 16:30 | Stefanie Jegelka (Massachusetts Institute of Technology, USA) Learning and Generalization in Graph Neural Networks | |
16:30 - 17:00 | Coffee Break | |
17:00 - 18:00 | Pierre Baldi (University of California, Irvine, USA) Neural Capacity and Attention | |
18:00 - 19:00 | Yasaman Bahri (Google Brain, USA) Dynamics & Phase Transitions in Wide, Deep Neural Networks | |
Friday, August 06, 2021 | ||
09:30 - 10:30 | Matthias Hein (University of Tübingen, Germany) Towards neural networks which know when they don't know | |
10:30 - 11:00 | Coffee Break | |
11:00 - 12:00 | Kathlén Kohn (KTH - Royal Institute of Technology, Sweden) The Geometry of Linear Convolutional Networks | |
12:00 - 12:30 | Luigi Malagò (Transylvanian Institute of Neuroscience (TINS) (Cluj-Napoca), Romania) Lagrangian and Hamiltonian Mechanics for Probabilities on the Statistical Bundle | |
12:30 - 13:00 | Kirandeep Kour (Max Planck Institute for Dynamics of Complex Technical Systems (Magdeburg), Germany) A Low-rank Support Tensor Network | |
13:00 - 14:00 | Lunch Break | |
14:00 - 14:30 | Matthias Löffler (ETH Zürich (Zurich), Switzerland) AdaBoost and robust one-bit compressed sensing | |
14:30 - 15:00 | Benjamin Fehrman (University of Oxford, United Kingdom) Convergence rates for stochastic gradient descent algorithms in non-convex loss landscapes | |
15:00 - 15:30 | Coffee Break | |
15:30 - 16:30 | Terry Lyons (University of Oxford, United Kingdom) From rough paths to streamed data | |
16:30 - 17:00 | Coffee Break | |
17:00 - 17:30 | Michael Murray (University of Oxford (Oxford, UK), United Kingdom) Activation Function Design for Deep Networks: Linearity and Effective Initialisation | |
17:30 - 18:00 | Daniel McKenzie (University of California, Los Angeles, USA) Learning to predict equilibria from data using fixed point networks | |
18:00 - 19:00 | Jeffrey Pennington (Google Brain, USA) Demystifying deep learning through high-dimensional statistics | |
19:00 | Conference Dinner | |
Saturday, August 07, 2021 | ||
09:30 - 10:30 | Arnulf Jentzen (Universität Münster, Germany) Convergence analysis for gradient flows in the training of artificial neural networks with ReLU activation | |
10:30 - 11:00 | Coffee Break | |
11:00 - 12:00 | Minh Hà Quang (RIKEN-AIP, Japan) Regularized information geometric and optimal transport distances between covariance operators and Gaussian processes | |
12:00 - 12:30 | Hanyuan Hang (University of Twente (Enschede), Netherlands) A Combination of Ensemble Methods for Large-Scale Regression | |
12:30 - 13:00 | Soon Hoe Lim (Nordita, KTH Royal Institute of Technology and Stockholm University, Sweden) Noisy Recurrent Neural Networks | |
13:00 - 14:00 | Lunch Break | |
14:00 - 14:30 | Guido Montúfar (Max Planck Institute for Mathematics in the Sciences (Leipzig), Germany, and UCLA ( ), USA) Implicit bias of gradient descent for mean squared error regression with wide neural networks | |
14:30 - 15:00 | Michael Schmischke (Chemnitz University of Technology, Germany) High-Dimensional Explainable ANOVA Approximation | |
15:00 - 15:30 | Coffee Break | |
15:30 - 16:00 | Sebastian Kassing (WWU Münster, Germany) Convergence of Stochastic Gradient Descent for Analytic Target Functions | |
16:00 - 16:30 | Burim Ramosaj (TU Dortmund, Germany) Interpretable Machines - Constructing valid Prediction Intervals with Random Forest | |
16:30 - 17:00 | Coffee Break | |
17:00 - 18:00 | Jason Lee (Princeton University, USA) Representation Learning | |
18:00 - 19:00 | Věra Kůrková (Czech Academy of Sciences, Czech Republic) Some implications of high-dimensional geometry for neurocomputing |
Date and Location
August 04 - 07, 2021 (previously planned for February 22 - 25, 2021)
Center for Interdisciplinary Research (ZiF), Bielefeld University
Methoden 1
33615 Bielefeld
Scientific Organizers
Benjamin Gess, MPI for Mathematics in the Sciences & Universität Bielefeld
Guido Montúfar, MPI for Mathematics in the Sciences & UCLA
Nihat Ay
Hamburg University of Technology
Institute of Data Science Foundations