| Coupling-based invertible neural networks are universal diffeomorphism approximators T Teshima, I Ishikawa, K Tojo, K Oono, M Ikeda, M Sugiyama Advances in Neural Information Processing Systems 33, 3362-3373, 2020 | 129 | 2020 |
| Universal approximation property of neural ordinary differential equations T Teshima, K Tojo, M Ikeda, I Ishikawa, K Oono arXiv preprint arXiv:2012.02414, 2020 | 55 | 2020 |
| Universal approximation property of invertible neural networks I Ishikawa, T Teshima, K Tojo, K Oono, M Ikeda, M Sugiyama Journal of Machine Learning Research 24 (287), 1-68, 2023 | 34 | 2023 |
| Metric on nonlinear dynamical systems with Perron-Frobenius operators I Ishikawa, K Fujii, M Ikeda, Y Hashimoto, Y Kawahara Advances in Neural Information Processing Systems 31, 2018 | 31 | 2018 |
| Krylov subspace method for nonlinear dynamical systems with random noise Y Hashimoto, I Ishikawa, M Ikeda, Y Matsuo, Y Kawahara Journal of Machine Learning Research 21 (172), 1-29, 2020 | 23 | 2020 |
| Fully-connected network on noncompact symmetric space and ridgelet transform based on helgason-fourier analysis S Sonoda, I Ishikawa, M Ikeda International Conference on Machine Learning, 20405-20422, 2022 | 20 | 2022 |
| Boundedness of composition operators on reproducing kernel Hilbert spaces with analytic positive definite functions M Ikeda, I Ishikawa, Y Sawano Journal of Mathematical Analysis and Applications 511 (1), 126048, 2022 | 19 | 2022 |
| Koopman and Perron–Frobenius operators on reproducing kernel Banach spaces M Ikeda, I Ishikawa, C Schlosser Chaos: An Interdisciplinary Journal of Nonlinear Science 32 (12), 2022 | 16 | 2022 |
| Ridge regression with over-parametrized two-layer networks converge to ridgelet spectrum S Sonoda, I Ishikawa, M Ikeda International Conference on Artificial Intelligence and Statistics, 2674-2682, 2021 | 16 | 2021 |
| Reproducing kernel Hilbert C*-module and kernel mean embeddings Y Hashimoto, I Ishikawa, M Ikeda, F Komura, T Katsura, Y Kawahara Journal of Machine Learning Research 22 (267), 1-56, 2021 | 13 | 2021 |
| Universality of group convolutional neural networks based on ridgelet analysis on groups S Sonoda, I Ishikawa, M Ikeda Advances in Neural Information Processing Systems 35, 38680-38694, 2022 | 11 | 2022 |
| Bounded composition operators on functional quasi-Banach spaces and stability of dynamical systems I Ishikawa Advances in Mathematics 424, 109048, 2023 | 10 | 2023 |
| Gamma factors for the Asai representation of GL2 SY Chen, Y Cheng, I Ishikawa Journal of Number Theory 209, 83-146, 2020 | 10 | 2020 |
| Koopman operators with intrinsic observables in rigged reproducing kernel Hilbert spaces I Ishikawa, Y Hashimoto, M Ikeda, Y Kawahara arXiv preprint arXiv:2403.02524, 2024 | 8 | 2024 |
| The global optimum of shallow neural network is attained by ridgelet transform S Sonoda, I Ishikawa, M Ikeda, K Hagihara, Y Sawano, T Matsubara, ... arXiv preprint arXiv:1805.07517, 2018 | 8 | 2018 |
| Boundedness of composition operators on Morrey spaces and weak Morrey spaces N Hatano, M Ikeda, I Ishikawa, Y Sawano Journal of Inequalities and Applications 2021, 1-15, 2021 | 7 | 2021 |
| Ghosts in Neural Networks: Existence S Sonoda, I Ishikawa, M Ikeda Structure and Role of Infinite-Dimensional Null Space 2106, 2021 | 7 | 2021 |
| A Global Universality of Two‐Layer Neural Networks with ReLU Activations N Hatano, M Ikeda, I Ishikawa, Y Sawano Journal of Function Spaces 2021 (1), 6637220, 2021 | 7 | 2021 |
| A unified Fourier slice method to derive ridgelet transform for a variety of depth-2 neural networks S Sonoda, I Ishikawa, M Ikeda Journal of Statistical Planning and Inference 233, 106184, 2024 | 6 | 2024 |
| Boundedness of composition operators on higher order Besov spaces in one dimension M Ikeda, I Ishikawa, K Taniguchi Mathematische Annalen 388 (4), 4487-4510, 2024 | 6 | 2024 |
Masahiro IkedaOsaka UniversityVerified email at ist.osaka-u.ac.jp
