Isao Ishikawa

According to our database, Isao Ishikawa authored at least 29 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Koopman Spectrum Nonlinear Regulators and Efficient Online Learning.

Motoya Ohnishi, Isao Ishikawa, Kendall Lowrey, Masahiro Ikeda, Sham M. Kakade, Yoshinobu Kawahara

Trans. Mach. Learn. Res., 2024

Constructive Universal Approximation Theorems for Deep Joint-Equivariant Networks by Schur's Lemma.

Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda

CoRR, 2024

Finite-dimensional approximations of push-forwards on locally analytic functionals and truncation of least-squares polynomials.

Isao Ishikawa

CoRR, 2024

Koopman operators with intrinsic observables in rigged reproducing kernel Hilbert spaces.

Isao Ishikawa, Yuka Hashimoto, Masahiro Ikeda, Yoshinobu Kawahara

CoRR, 2024

A unified Fourier slice method to derive ridgelet transform for a variety of depth-2 neural networks.

Sho Sonoda, Isao Ishikawa, Masahiro Ikeda

CoRR, 2024

Koopman-based generalization bound: New aspect for full-rank weights.

Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Atsushi Nitanda, Taiji Suzuki

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Generalized Eigenvalues of the Perron-Frobenius Operators of Symbolic Dynamical Systems.

Hayato Chiba, Masahiro Ikeda, Isao Ishikawa

SIAM J. Appl. Dyn. Syst., December, 2023

Universal Approximation Property of Invertible Neural Networks.

Isao Ishikawa, Takeshi Teshima, Koichi Tojo, Kenta Oono, Masahiro Ikeda, Masashi Sugiyama

J. Mach. Learn. Res., 2023

Joint Group Invariant Functions on Data-Parameter Domain Induce Universal Neural Networks.

Sho Sonoda, Hideyuki Ishi, Isao Ishikawa, Masahiro Ikeda

CoRR, 2023

Deep Ridgelet Transform: Voice with Koopman Operator Proves Universality of Formal Deep Networks.

Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda

CoRR, 2023

Koopman-Based Bound for Generalization: New Aspect of Neural Networks Regarding Nonlinear Noise Filtering.

Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Atsushi Nitanda, Taiji Suzuki

CoRR, 2023

2022

Dynamic Structure Estimation from Bandit Feedback.

Motoya Ohnishi, Isao Ishikawa, Yuko Kuroki, Masahiro Ikeda

CoRR, 2022

Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups.

Sho Sonoda, Isao Ishikawa, Masahiro Ikeda

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis.

Sho Sonoda, Isao Ishikawa, Masahiro Ikeda

Proceedings of the International Conference on Machine Learning, 2022

2021

Reproducing kernel Hilbert C*-module and kernel mean embeddings.

Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda, Fuyuta Komura, Takeshi Katsura, Yoshinobu Kawahara

J. Mach. Learn. Res., 2021

Koopman Spectrum Nonlinear Regulator and Provably Efficient Online Learning.

Motoya Ohnishi, Isao Ishikawa, Kendall Lowrey, Masahiro Ikeda, Sham M. Kakade, Yoshinobu Kawahara

CoRR, 2021

Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null Space.

Sho Sonoda, Isao Ishikawa, Masahiro Ikeda

CoRR, 2021

Ridge Regression with Over-parametrized Two-Layer Networks Converge to Ridgelet Spectrum.

Sho Sonoda, Isao Ishikawa, Masahiro Ikeda

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Krylov Subspace Method for Nonlinear Dynamical Systems with Random Noise.

Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda, Yoichi Matsuo, Yoshinobu Kawahara

J. Mach. Learn. Res., 2020

Universal Approximation Property of Neural Ordinary Differential Equations.

Takeshi Teshima, Koichi Tojo, Masahiro Ikeda, Isao Ishikawa, Kenta Oono

CoRR, 2020

A global universality of two-layer neural networks with ReLU activations.

Naoya Hatano, Masahiro Ikeda, Isao Ishikawa, Yoshihiro Sawano

CoRR, 2020

Kernel Mean Embeddings of Von Neumann-Algebra-Valued Measures.

Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda, Fuyuta Komura, Yoshinobu Kawahara

CoRR, 2020

Gradient Descent Converges to Ridgelet Spectrum.

Sho Sonoda, Isao Ishikawa, Masahiro Ikeda

CoRR, 2020

Analysis via Orthonormal Systems in Reproducing Kernel Hilbert C^*-Modules and Applications.

Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda, Fuyuta Komura, Takeshi Katsura, Yoshinobu Kawahara

CoRR, 2020

Coupling-based Invertible Neural Networks Are Universal Diffeomorphism Approximators.

Takeshi Teshima, Isao Ishikawa, Koichi Tojo, Kenta Oono, Masahiro Ikeda, Masashi Sugiyama

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

Metric on random dynamical systems with vector-valued reproducing kernel Hilbert spaces.

Isao Ishikawa, Akinori Tanaka, Masahiro Ikeda, Yoshinobu Kawahara

CoRR, 2019

2018

Metric on Nonlinear Dynamical Systems with Koopman Operators.

Isao Ishikawa, Keisuke Fujii, Masahiro Ikeda, Yuka Hashimoto, Yoshinobu Kawahara

CoRR, 2018

Integral representation of the global minimizer.

Sho Sonoda, Isao Ishikawa, Masahiro Ikeda, Kei Hagihara, Yoshihiro Sawano, Takuo Matsubara, Noboru Murata

CoRR, 2018

Metric on Nonlinear Dynamical Systems with Perron-Frobenius Operators.

Isao Ishikawa, Keisuke Fujii, Masahiro Ikeda, Yuka Hashimoto, Yoshinobu Kawahara

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018