| On the number of linear regions of deep neural networks GF Montufar, R Pascanu, K Cho, Y Bengio Advances in neural information processing systems 27, 2014 | 2841 | 2014 |
| On the number of response regions of deep feed forward networks with piece-wise linear activations R Pascanu, G Montufar, Y Bengio International Conference on Learning Representations (ICLR) 2014, Banff …, 2013 | 377 | 2013 |
| Weisfeiler and lehman go topological: Message passing simplicial networks C Bodnar, F Frasca, YG Wang, N Otter, G Montúfar, P Lio, M Bronstein 38th International Conference on Machine Learning (ICML), 1026-1037, 2021 | 292 | 2021 |
| Weisfeiler and lehman go cellular: Cw networks C Bodnar, F Frasca, N Otter, YG Wang, P Liò, GF Montufar, M Bronstein Advances in Neural Information Processing Systems (NeurIPS) 35, 2021 | 291 | 2021 |
| Refinements of universal approximation results for deep belief networks and restricted Boltzmann machines G Montufar, N Ay Neural computation 23 (5), 1306-1319, 2011 | 117 | 2011 |
| Haar graph pooling YG Wang, M Li, Z Ma, G Montufar, X Zhuang, Y Fan 37th International conference on machine learning (ICML), 9952-9962, 2020 | 101 | 2020 |
| Optimal Transport to a Variety TÖ Çelik, A Jamneshan, G Montufar, B Sturmfels, L Venturello Mathematical Aspects of Computer and Information Sciences, 364-381, 2019 | 83* | 2019 |
| Natural gradient via optimal transport W Li, G Montúfar Information Geometry 1, 181-214, 2018 | 82 | 2018 |
| Tight bounds on the smallest eigenvalue of the neural tangent kernel for deep relu networks Q Nguyen, M Mondelli, GF Montufar 38th International Conference on Machine Learning (ICML), 8119-8129, 2021 | 81 | 2021 |
| Restricted boltzmann machines: Introduction and review G Montúfar Information Geometry and Its Applications: On the Occasion of Shun-ichi …, 2018 | 79 | 2018 |
| How framelets enhance graph neural networks X Zheng, B Zhou, J Gao, YG Wang, P Lio, M Li, G Montúfar 38th International Conference on Machine Learning (ICML), 12761-12771, 2021 | 74 | 2021 |
| Expressive power and approximation errors of restricted Boltzmann machines GF Montúfar, J Rauh, N Ay Advances in Neural Information Processing Systems (NeurIPS) 24, 415-423, 2011 | 62 | 2011 |
| FoSR: First-order spectral rewiring for addressing oversquashing in GNNs K Karhadkar, PK Banerjee, G Montúfar International Conference on Learning Representations (ICLR) 2023, 2022 | 60 | 2022 |
| Cell graph neural networks enable the precise prediction of patient survival in gastric cancer Y Wang, YG Wang, C Hu, M Li, Y Fan, N Otter, I Sam, H Gou, Y Hu, ... NPJ precision oncology 6 (1), 45, 2022 | 55* | 2022 |
| Universal Approximation Depth and Errors of Narrow Belief Networks with Discrete Units GF Montúfar Neural Computation 26 (7), 1386-1407, 2014 | 54 | 2014 |
| Oversquashing in GNNs through the lens of information contraction and graph expansion PK Banerjee, K Karhadkar, YG Wang, U Alon, G Montúfar 58th Annual Allerton Conference on Communication, Control, and Computing, 2022 | 51 | 2022 |
| Wasserstein of Wasserstein loss for learning generative models Y Dukler, W Li, A Tong Lin, G Montúfar 36th International Conference on Machine Learning (ICML) 97, 1716-1725, 2019 | 46 | 2019 |
| Notes on the number of linear regions of deep neural networks G Montúfar eScholarship, University of California, 2017 | 46 | 2017 |
| When Does a Mixture of Products Contain a Product of Mixtures? GF Montúfar, J Morton SIAM Journal on Discrete Mathematics 29 (1), 321-347, 2015 | 46 | 2015 |
| Wasserstein Proximal of GANs A Tong Lin, W Li, S Osher, G Montúfar 5th International Conference Geometric Science of Information, 2018 | 44* | 2018 |
Nihat AyHamburg University of Technology, Institute for Data Science FoundationsVerified email at tuhh.de
