Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Mario Geiger

How memory architecture affects performance and learning in simple POMDPs


Jun 16, 2021
Mario Geiger, Christophe Eloy, Matthieu Wyart


  Access Paper or Ask Questions

SE(3)-equivariant prediction of molecular wavefunctions and electronic densities


Jun 04, 2021
Oliver T. Unke, Mihail Bogojeski, Michael Gastegger, Mario Geiger, Tess Smidt, Klaus-Robert Müller


  Access Paper or Ask Questions

Relative stability toward diffeomorphisms in deep nets indicates performance


May 06, 2021
Leonardo Petrini, Alessandro Favero, Mario Geiger, Matthieu Wyart


  Access Paper or Ask Questions

Perspective: A Phase Diagram for Deep Learning unifying Jamming, Feature Learning and Lazy Training


Dec 30, 2020
Mario Geiger, Leonardo Petrini, Matthieu Wyart


  Access Paper or Ask Questions

Geometric compression of invariant manifolds in neural nets


Aug 28, 2020
Jonas Paccolat, Leonardo Petrini, Mario Geiger, Kevin Tyloo, Matthieu Wyart


  Access Paper or Ask Questions

Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties


Aug 22, 2020
Benjamin Kurt Miller, Mario Geiger, Tess E. Smidt, Frank Noé

* NeurIPS 2020 Machine Learning for Molecules 

  Access Paper or Ask Questions

Compressing invariant manifolds in neural nets


Jul 22, 2020
Jonas Paccolat, Leonardo Petrini, Mario Geiger, Kevin Tyloo, Matthieu Wyart


  Access Paper or Ask Questions

Finding Symmetry Breaking Order Parameters with Euclidean Neural Networks


Jul 04, 2020
Tess E. Smidt, Mario Geiger, Benjamin Kurt Miller

* 6 pages, 3 figures 

  Access Paper or Ask Questions

Disentangling feature and lazy learning in deep neural networks: an empirical study


Jun 19, 2019
Mario Geiger, Stefano Spigler, Arthur Jacot, Matthieu Wyart


  Access Paper or Ask Questions

Asymptotic learning curves of kernel methods: empirical data v.s. Teacher-Student paradigm


Jun 06, 2019
Stefano Spigler, Mario Geiger, Matthieu Wyart


  Access Paper or Ask Questions

Scaling description of generalization with number of parameters in deep learning


Jan 18, 2019
Mario Geiger, Arthur Jacot, Stefano Spigler, Franck Gabriel, Levent Sagun, Stéphane d'Ascoli, Giulio Biroli, Clément Hongler, Matthieu Wyart


  Access Paper or Ask Questions

A General Theory of Equivariant CNNs on Homogeneous Spaces


Nov 05, 2018
Taco Cohen, Mario Geiger, Maurice Weiler


  Access Paper or Ask Questions

3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data


Oct 27, 2018
Maurice Weiler, Mario Geiger, Max Welling, Wouter Boomsma, Taco Cohen


  Access Paper or Ask Questions

A jamming transition from under- to over-parametrization affects loss landscape and generalization


Oct 22, 2018
Stefano Spigler, Mario Geiger, Stéphane d'Ascoli, Levent Sagun, Giulio Biroli, Matthieu Wyart

* 11 pages, 6 figures, submitted to NIPS workshop "Integration of Deep Learning Theories". arXiv admin note: substantial text overlap with arXiv:1809.09349 

  Access Paper or Ask Questions

The jamming transition as a paradigm to understand the loss landscape of deep neural networks


Oct 03, 2018
Mario Geiger, Stefano Spigler, Stéphane d'Ascoli, Levent Sagun, Marco Baity-Jesi, Giulio Biroli, Matthieu Wyart


  Access Paper or Ask Questions

Intertwiners between Induced Representations (with Applications to the Theory of Equivariant Neural Networks)


Mar 30, 2018
Taco S. Cohen, Mario Geiger, Maurice Weiler


  Access Paper or Ask Questions

Spherical CNNs


Feb 25, 2018
Taco S. Cohen, Mario Geiger, Jonas Koehler, Max Welling

* Proceedings of the 6th International Conference on Learning Representations (ICLR), 2018 

  Access Paper or Ask Questions

Convolutional Networks for Spherical Signals


Sep 15, 2017
Taco Cohen, Mario Geiger, Jonas Köhler, Max Welling


  Access Paper or Ask Questions