| Graph neural networks exponentially lose expressive power for node classification K Oono, T Suzuki arXiv preprint arXiv:1905.10947, 2019 | 1108 | 2019 |
| Density ratio estimation in machine learning M Sugiyama, T Suzuki, T Kanamori Cambridge University Press, 2012 | 860 | 2012 |
| Direct importance estimation for covariate shift adaptation M Sugiyama, T Suzuki, S Nakajima, H Kashima, P Von Bünau, ... Annals of the Institute of Statistical Mathematics 60 (4), 699-746, 2008 | 585 | 2008 |
| Adaptivity of deep ReLU network for learning in Besov and mixed smooth Besov spaces: optimal rate and curse of dimensionality T Suzuki International Conference on Learning Representations, 2019 | 361 | 2019 |
| Density-ratio matching under the bregman divergence: a unified framework of density-ratio estimation M Sugiyama, T Suzuki, T Kanamori Annals of the Institute of Statistical Mathematics 64 (5), 1009-1044, 2012 | 274 | 2012 |
| High-dimensional asymptotics of feature learning: How one gradient step improves the representation J Ba, MA Erdogdu, T Suzuki, Z Wang, D Wu, G Yang Advances in Neural Information Processing Systems 35, 37932-37946, 2022 | 224 | 2022 |
| Relative density-ratio estimation for robust distribution comparison M Yamada, T Suzuki, T Kanamori, H Hachiya, M Sugiyama Neural computation 25 (5), 1324-1370, 2013 | 198 | 2013 |
| Statistical performance of convex tensor decomposition R Tomioka, T Suzuki, K Hayashi, H Kashima Advances in neural information processing systems 24, 2011 | 197 | 2011 |
| Dual averaging and proximal gradient descent for online alternating direction multiplier method T Suzuki International Conference on Machine Learning, 392-400, 2013 | 190 | 2013 |
| Diffusion models are minimax optimal distribution estimators K Oko, S Akiyama, T Suzuki International Conference on Machine Learning, 26517-26582, 2023 | 188 | 2023 |
| Convex tensor decomposition via structured schatten norm regularization R Tomioka, T Suzuki Advances in neural information processing systems 26, 2013 | 176 | 2013 |
| Approximating mutual information by maximum likelihood density ratio estimation T Suzuki, M Sugiyama, J Sese, T Kanamori New challenges for feature selection in data mining and knowledge discovery …, 2008 | 173 | 2008 |
| Mutual information estimation reveals global associations between stimuli and biological processes T Suzuki, M Sugiyama, T Kanamori, J Sese BMC bioinformatics 10 (Suppl 1), S52, 2009 | 160 | 2009 |
| Statistical analysis of kernel-based least-squares density-ratio estimation T Kanamori, T Suzuki, M Sugiyama Machine Learning 86 (3), 335-367, 2012 | 154 | 2012 |
| Relative density-ratio estimation for robust distribution comparison M Yamada, T Suzuki, T Kanamori, H Hachiya, M Sugiyama Advances in neural information processing systems 24, 2011 | 133 | 2011 |
| Super-Linear Convergence of Dual Augmented Lagrangian Algorithm for Sparsity Regularized Estimation. R Tomioka, T Suzuki, M Sugiyama Journal of Machine Learning Research 12 (5), 2011 | 114 | 2011 |
| Stochastic particle gradient descent for infinite ensembles A Nitanda, T Suzuki arXiv preprint arXiv:1712.05438, 2017 | 113 | 2017 |
| Convex analysis of the mean field langevin dynamics A Nitanda, D Wu, T Suzuki International Conference on Artificial Intelligence and Statistics, 9741-9757, 2022 | 110 | 2022 |
| Generalization of two-layer neural networks: An asymptotic viewpoint J Ba, M Erdogdu, T Suzuki, D Wu, T Zhang International conference on learning representations, 2020 | 105 | 2020 |
| Least-squares conditional density estimation M Sugiyama, I Takeuchi, T Suzuki, T Kanamori, H Hachiya, D Okanohara IEICE Transactions on Information and Systems 93 (3), 583-594, 2010 | 104 | 2010 |
Masashi SugiyamaDirector, RIKEN Center for Advanced Intelligence Project / Professor, The University of TokyoVerified email at k.u-tokyo.ac.jp
