ジャーナル論文 / Journal
  1. Sasaki, H., and Takenouchi, T., "Outlier-robust parameter estimation for unnormalized statistical models", Jpn. J. Stat. Data Sci., (2024).
  2. Nakagawa, T., Sanada, Y., Waida, H., Zhang, Y., Wada, Y., Takanashi, K., Yamada, T., and Kanamori, T., "Denoising cosine similarity: A theory-driven approach for efficient representation learning", Neural Netw., (2024).
  3. 園田翔, "積分表現ニューラルネットとリッジレット変換", 応用数理 33(1), 4–13, (2023).
  4. Zhang, Y., Wada, Y., Waida, H., Goto, K., Hino, Y., and Kanamori, T., "Deep Clustering with a Constraint for Topological Invariance based on Symmetric InfoNCE", Neural Comput., (2023).
  5. Watanabe, K., Sakamoto, K., Karakida, R., Sonoda, S., and Amari, S., "Deep learning in random neural fields: Numerical experiments via neural tangent kernel", Neural Netw. 160, 148–163, (2023).
  6. Wang, H., Jieyu, Z., Zhu, Q., Huang, W., Kawaguchi, K., and Xiao, X., "Single-pass contrastive learning can work for both homophilic and heterophilic graph", Transactions on Machine Learning Research, (2023).
  7. Huang, W., Liu, C., Chen, Y., Xu, R. Y., Zhang, M., and Weng, T., "Analyzing Deep PAC-Bayesian Learning with Neural Tangent Kernel: Convergence, Analytic Generalization Bound, and Efficient Hyperparameter Selection", Transactions on Machine Learning Research, (2023).
  8. Guan, S., Yu, X., Huang, W., Fang, G., and Lu, H., "DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition", IEEE Trans. Image Processing 33, 395–407, (2023).
  9. Andéol, L., Kawakami, Y., Wada, Y., Kanamori, T., Müller, K., and Montavon, G., "Learning domain invariant representations by joint Wasserstein distance minimization", Neural Netw. 167, 233–243, (2023).
  10. Tanimoto, A., Yamada, S., Takenouchi, T., Sugiyama, M., and Kashima, H., "Improving imbalanced classification using near-miss instances", Expert Syst. Appl. 201(117130), 1–15, (2022).
  11. Sasaki, H., and Takenouchi, T., "Representation Learning for Maximization of MI, Nonlinear ICA and Nonlinear Subspaces with Robust Density Ratio Estimation", J. Mach. Learn. Res. 231, 1–55, (2022).
  12. Nitanda, A., Wu, D., and Suzuki, T., "Particle Dual Averaging: Optimization of Mean Field Neural Networks with Global Convergence Rate Analysis", J. Stat. Mech: Theory Exp. 2022(11), 114010, (2022).
  13. Liu, S., Kanamori, T., and Williams, D., "Estimating Density Models with Truncation Boundaries using Score Matching", Journal of Machine Learning Research , (2022).
  14. Kumagai, W., Sannai, A., and Kawano, M., "Universal approximation with neural networks on function spaces", J. Exp. Theor. Artif. Intell., (2022).
  15. Ishikawa, I., Teshima, T., Tojo, K., Oono, K., Ikeda, M., and Sugiyama, M., "Universal approximation property of invertible neural networks.", CoRR abs/2204.07415, (2022).
  16. Sonoda, S., Ishikawa, I., and Ikeda, M., "Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null Space.", CoRR abs/2106.04770, (2021).
  17. Mae, Y., Kumagai, W., and Kanamori, T., "Uncertainty Propagation for Dropout-based Bayesian Neural Networks", Neural Netw., (2021).
国際会議 / Proceedings
  1. Sonoda, S., Ishi, H., Ishikawa, I., and Ikeda, M., "Joint Group Invariant Functions on Data-Parameter Domain Induce Universal Neural Networks", Proceedings on Symmetry and Geometry in Neural Representations, (2024).
  2. Sonoda, S., Hashimoto, Y., Ishikawa, I., and Ikeda, M., "Deep Ridgelet Transform: Voice with Koopman Operator Proves Universality of Formal Deep Networks", Proceedings on Symmetry and Geometry in Neural Representations, (2024).
  3. Yamasaki, H., Subramanian, S., Hayakawa, s., and Sonoda, S., "Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation", Icml, (2023).
  4. Wimalawarne, K., and Taiji, S., "Layer-wise Adaptive Graph Convolution Networks Using Generalized Pagerank", Proceedings of The 14th Asian Conference on Machine Learning (ACML2023) 189, 1117–1117, (2023).
  5. Takakura, S., and Suzuki, T., "Approximation and Estimation Ability of Transformers for Sequence-to-Sequence Functions with Infinite Dimensional Input", Proceedings of the 40th International Conference on Machine Learning (ICML2023), (2023).
  6. Suzuki, T., Wu, D., and Nitanda, A., "Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond", Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS2023), (2023).
  7. Suzuki, T., Wu, D., and Nitanda, A., "Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction", Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS2023), (2023).
  8. Suzuki, T., Nitanda, A., and Wu, D., "Uniform-in-time propagation of chaos for the mean field gradient Langevin dynamics", The Eleventh International Conference on Learning Representations, (2023).
  9. Suzuki, A., Nitanda, A., Suzuki , T., Wang, J., Tian, F., and Yamanishi, K., "Tight and fast generalization error bound of graph embedding in metric space", Proceedings of the 40th International Conference on Machine Learning, (2023).
  10. Nitta, S., Suzuki, T., Mulet, A. R., Yaguchi, A., and Hirai, R., "Scalable Federated Learning for Clients with Different Input Image Sizes and Numbers of Output Categories", Proceedings of the 22nd IEEE International Conference on Machine Learning and Applications (ICMLA2023), (2023).
  11. Nitanda, A., Oko, K., Wu, D., Takenouchi, N., and Suzuki, T., "Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems", Proceedings of the 40th International Conference on Machine Learning (ICML2023), (2023).
  12. Murata, T., and Suzuki, T., "DIFF2: Differential Private Optimization via Gradient Differences for Nonconvex Distributed Learning", Proceedings of the 40th International Conference on Machine Learning (ICML2023), (2023).
  13. Mikami, H., Fukumizu, K., Murai, S., Suzuki, S., Kikuchi, Y., Suzuki, T., Maeda, S., and Hayashi, K., "A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?", Proceedings of Machine Learning and Knowledge Discovery in Databases, Part III, Lecture Notes in Computer Science 13715, 477–492, (2023).
  14. Li, M., Sonoda, S., Cao, F., Wang, Y., and Liang, J., "How Powerful are Shallow Neural Networks with Bandlimited Random Weights?", Icml, (2023).
  15. Kingetsu, H., Kobayashi, K., and Suzuki, T., "Neural Network Module Decomposition and Recomposition with Superimposed Masks", International Joint Conference on Neural Networks (IJCNN), (2023).
  16. Huang, W., Yongqiang, C., Kaiwen, Z., Yatao, B., Bo, H., and James, C., "Understanding and Improving Feature Learning for Out-of-Distribution Generalization", NeurIPS 2023, (2023).
  17. Chen, Y., Huang, W., Wang, H., Loh, C., Srivastava, A., Nguyen, L. M., and Weng, T., "Analyzing Generalization of Neural Networks through Loss Path Kernels", NeurIPS 2023, (2023).
  18. Cai, Z., Shi, Y., Huang, W., and Wang, J., "Fed-CO2: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning", NeurIPS 2023, (2023).
  19. Ba, J., Erdogdu, M. A., Suzuki, T., Wang, Z., and Wu, D., "Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective", Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS2023), (2023).
  20. Alireza , M., Wu , D., Suzuki , T., and Erdogdu, M. A., "Gradient-Based Feature Learning under Structured Data", Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS2023), (2023).
  21. Akiyama, S., and Suzuki, T., "Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods", The Eleventh International Conference on Learning Representations (ICLR2023), (2023).
  22. Xu, C., Haruki, K., Suzuki, T., Ozawa, M., Uematsu, K., and Sakai, R., "Data-Parallel Momentum Diagonal Empirical Fisher (DP-MDEF): Adaptive Gradient Method is Affected by Hessian Approximation and Multi-Class Data", 21st IEEE International Conference on Machine Learning and Applications (ICMLA), 1397–1404, (2022).
  23. Tomoya, M., and Suzuki, T., "Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning", Advances in Neural Information Processing Systems 35 (NeurIPS 2022) 35, 5039–5051, (2022).
  24. Sonoda, S., Ishikawa, I., and Ikeda, M., "Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups", Advances in Neural Information Processing Systems 35, 38680–38694, (2022).
  25. Sonoda, S., Ishikawa, I., and Ikeda, M., "Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis.", Icml, 20405–20422, (2022).
  26. Okumoto, S., and Suzuki, T., "Learnability of convolutional neural networks for infinite dimensional input via mixed and anisotropic smoothness", The Tenth International Conference on Learning Representations (ICLR2022), (2022).
  27. Oko, K., Suzuki, T., Nitanda, A., and Wu, D., "Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization", The Tenth International Conference on Learning Representations (ICLR2022), (2022).
  28. Nitanda, A., Wu, D., and Suzuki, T., "Convex Analysis of the Mean Field Langevin Dynamics.", Proceedings of The 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022) 151, 9741–9757, (2022).
  29. Nishikawa, N., Suzuki, T., Nitanda, A., and Wu, D., "Two-layer neural network on infinite dimensional data: Global optimization guarantee in the mean-field regime", Advances in Neural Information Processing Systems 35 (NeurIPS 2022) 35, 32612–32623, (2022).
  30. Muzellec, B., Sato, K., Massias, M., and Suzuki, T., "Dimension-free convergence rates for gradient Langevin dynamics in RKHS", Proceedings of Thirty Fifth Conference on Learning Theory (COLT2022) 178, 1356–1420, (2022).
  31. Kinoshita, Y., and Suzuki, T., "Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization", Advances in Neural Information Processing Systems 35 (NeurIPS 2022) 35, 19022–19034, (2022).
  32. Huang, W., Zhang, M., and Yang, B., "Interpreting Operation Selection in Differentiable Architecture Search: A Perspective from Influence-Directed Explanations", NeurIPS 2022, (2022).
  33. Chen, W., Gong, X., Hanin, B., Wang, Z., and Huang, W., "Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis.", NeurIPS 2022 abs/2205.05662, (2022).
  34. Ba, J., Erdogdu, M. A., Suzuki, T., Wang, Z., Wu, D., and Greg , Y., "High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation", Advances in Neural Information Processing Systems 35 (NeurIPS 2022) 35, 37932–37946, (2022).
  35. Ba, J., Erdogdu, M. A., Ghassemi, M., Sun, S., Suzuki, T., Wu, D., and Zhang, T., "Understanding the Variance Collapse of SVGD in High Dimensions", The Tenth International Conference on Learning Representations (ICLR2022), (2022).
  36. Sonoda, S., Ishikawa, I., and Ikeda, M., "Ridge Regression with Over-parametrized Two-Layer Networks Converge to Ridgelet Spectrum.", Aistats, 2674–2682, (2021).
  37. Massaroli, S., Poli, M., Sonoda, S., Suzuki, T., Park, J., Yamashita, A., and Asama, H., "Differentiable Multiple Shooting Layers", Advances in Neural Information Processing Systems (NeurIPS2021) 34, 16532–16544, (2021).