Spherical cnns TS Cohen, M Geiger, J Köhler, M Welling arXiv preprint arXiv:1801.10130, 2018 | 364 | 2018 |
3d steerable cnns: Learning rotationally equivariant features in volumetric data M Weiler, M Geiger, M Welling, W Boomsma, T Cohen arXiv preprint arXiv:1807.02547, 2018 | 110 | 2018 |
A general theory of equivariant cnns on homogeneous spaces T Cohen, M Geiger, M Weiler arXiv preprint arXiv:1811.02017, 2018 | 74 | 2018 |
Jamming transition as a paradigm to understand the loss landscape of deep neural networks M Geiger, S Spigler, S d'Ascoli, L Sagun, M Baity-Jesi, G Biroli, M Wyart Physical Review E 100 (1), 012115, 2019 | 66 | 2019 |
Scaling description of generalization with number of parameters in deep learning M Geiger, A Jacot, S Spigler, F Gabriel, L Sagun, S d’Ascoli, G Biroli, ... Journal of Statistical Mechanics: Theory and Experiment 2020 (2), 023401, 2020 | 64 | 2020 |
Comparing dynamics: Deep neural networks versus glassy systems M Baity-Jesi, L Sagun, M Geiger, S Spigler, GB Arous, C Cammarota, ... International Conference on Machine Learning, 314-323, 2018 | 55 | 2018 |
Convolutional networks for spherical signals T Cohen, M Geiger, J Köhler, M Welling arXiv preprint arXiv:1709.04893, 2017 | 51 | 2017 |
A jamming transition from under-to over-parametrization affects loss landscape and generalization S Spigler, M Geiger, S d'Ascoli, L Sagun, G Biroli, M Wyart arXiv preprint arXiv:1810.09665, 2018 | 38 | 2018 |
Deep convolutional neural networks as strong gravitational lens detectors C Schaefer, M Geiger, T Kuntzer, JP Kneib Astronomy & Astrophysics 611, A2, 2018 | 31 | 2018 |
A jamming transition from under-to over-parametrization affects generalization in deep learning S Spigler, M Geiger, S d’Ascoli, L Sagun, G Biroli, M Wyart Journal of Physics A: Mathematical and Theoretical 52 (47), 474001, 2019 | 28 | 2019 |
The strong gravitational lens finding challenge RB Metcalf, M Meneghetti, C Avestruz, F Bellagamba, CR Bom, E Bertin, ... Astronomy & Astrophysics 625, A119, 2019 | 27 | 2019 |
Intertwiners between induced representations (with applications to the theory of equivariant neural networks) TS Cohen, M Geiger, M Weiler arXiv preprint arXiv:1803.10743, 2018 | 25 | 2018 |
Thermal solar collector with VO2 absorber coating and V1-xWxO2 thermochromic glazing–Temperature matching and triggering A Paone, M Geiger, R Sanjines, A Schüler Solar energy 110, 151-159, 2014 | 22 | 2014 |
Disentangling feature and lazy learning in deep neural networks: an empirical study. M Geiger, S Spigler, A Jacot, M Wyart | 13 | 2019 |
Embedded microstructures for daylighting and seasonal thermal control A Kostro, M Geiger, N Jolissaint, MAG Lazo, JL Scartezzini, Y Leterrier, ... Nonimaging Optics: Efficient Design for Illumination and Solar Concentration …, 2012 | 11 | 2012 |
Disentangling feature and lazy training in deep neural networks M Geiger, S Spigler, A Jacot, M Wyart Journal of Statistical Mechanics: Theory and Experiment 2020 (11), 113301, 2020 | 9 | 2020 |
Relevance of rotationally equivariant convolutions for predicting molecular properties BK Miller, M Geiger, TE Smidt, F Noé arXiv preprint arXiv:2008.08461, 2020 | 9 | 2020 |
Asymptotic learning curves of kernel methods: empirical data vs Teacher-Student paradigm S Spigler, M Geiger, M Wyart arXiv preprint arXiv:1905.10843, 2019 | 6 | 2019 |
CFSpro: ray tracing for design and optimization of complex fenestration systems using mixed dimensionality approach A Kostro, M Geiger, JL Scartezzini, A Schüler Applied optics 55 (19), 5127-5134, 2016 | 6 | 2016 |
3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data. 2018 M Weiler, M Geiger, M Welling, W Boomsma, T Cohen URL http://arxiv. org/abs, 1807 | 6 | 1807 |