| Deep neural networks learn non-smooth functions effectively M Imaizumi, K Fukumizu Artificial Intelligence and Statistics, 869-878, 2019 | 162 | 2019 |
| Adaptive Approximation and Generalization of Deep Neural Network with Intrinsic Dimensionality. R Nakada, M Imaizumi Journal of Machine Learning Research 21 (174), 1-38, 2020 | 159* | 2020 |
| Finite sample analysis of minimax offline reinforcement learning: Completeness, fast rates and first-order efficiency M Uehara, M Imaizumi, N Jiang, N Kallus, W Sun, T Xie arXiv preprint arXiv:2102.02981, 2021 | 60 | 2021 |
| PCA-based estimation for functional linear regression with functional responses M Imaizumi, K Kato Journal of Multivariate Analysis 163, 15-36, 2018 | 43 | 2018 |
| Improved generalization bounds of group invariant/equivariant deep networks via quotient feature spaces A Sannai, M Imaizumi, M Kawano Uncertainty in artificial intelligence, 771-780, 2021 | 42 | 2021 |
| On tensor train rank minimization: Statistical efficiency and scalable algorithm M Imaizumi, T Maehara, K Hayashi Advances in Neural Information Processing Systems 30, 2017 | 39 | 2017 |
| Instrumental variable regression via kernel maximum moment loss R Zhang, M Imaizumi, B Schölkopf, K Muandet Journal of Causal Inference 11 (1), 20220073, 2023 | 36* | 2023 |
| Doubly decomposing nonparametric tensor regression M Imaizumi, K Hayashi International conference on machine learning, 727-736, 2016 | 31 | 2016 |
| Advantage of deep neural networks for estimating functions with singularity on hypersurfaces M Imaizumi, K Fukumizu Journal of Machine Learning Research 23 (1), 4772-4825, 2022 | 28* | 2022 |
| Tensor decomposition with smoothness M Imaizumi, K Hayashi International conference on machine learning, 1597-1606, 2017 | 22 | 2017 |
| On random subsampling of Gaussian process regression: A graphon-based analysis K Hayashi, M Imaizumi, Y Yoshida Artificial Intelligence and Statistics, 2055-2065, 2020 | 18 | 2020 |
| A simple method to construct confidence bands in functional linear regression M Imaizumi, K Kato Statistica Sinica 29 (4), 2055-2081, 2019 | 15 | 2019 |
| Hypothesis test and confidence analysis with wasserstein distance on general dimension M Imaizumi, H Ota, T Hamaguchi Neural Computation 34 (6), 1448-1487, 2022 | 12 | 2022 |
| Learning causal models from conditional moment restrictions by importance weighting M Kato, M Imaizumi, K McAlinn, H Kakehi, S Yasui International Conference on Learning Representation, 2021 | 8 | 2021 |
| Inference for projection-based wasserstein distances on finite spaces R Okano, M Imaizumi Statistica Sinica, 2022 | 7 | 2022 |
| On generalization bounds for deep networks based on loss surface implicit regularization M Imaizumi, J Schmidt-Hieber IEEE Transactions on Information Theory 69 (2), 1203-1223, 2022 | 6 | 2022 |
| Benign overfitting in time series linear model with over-parameterization S Nakakita, M Imaizumi arXiv preprint arXiv:2204.08369, 2022 | 6 | 2022 |
| Statistically efficient estimation for non-smooth probability densities M Imaizumi, T Maehara, Y Yoshida Artificial Intelligence and Statistics, 978-987, 2018 | 6 | 2018 |
| Exponential escape efficiency of SGD from sharp minima in non-stationary regime H Ibayashi, M Imaizumi arXiv preprint arXiv:2111.04004, 2021 | 5 | 2021 |
| Fréchet kernel for trajectory data analysis K Takeuchi, M Imaizumi, S Kanda, Y Tabei, K Fujii, K Yoda, M Ishihata, ... Proceedings of the 29th International Conference on Advances in Geographic …, 2021 | 5 | 2021 |
Kenji FukumizuThe Institute of Statistical Mathematics在 ism.ac.jp 的电子邮件经过验证
