Sho Sonoda

CoRR, 2024

A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees.

[BibT_eX]

[DOI]

CoRR, 2024

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

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Deep learning in random neural fields: Numerical experiments via neural tangent kernel.

[BibT_eX]

[DOI]

Neural Networks, March, 2023

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

[BibT_eX]

[DOI]

CoRR, 2023

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

[BibT_eX]

[DOI]

CoRR, 2023

LPML: LLM-Prompting Markup Language for Mathematical Reasoning.

[BibT_eX]

[DOI]

CoRR, 2023

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

[BibT_eX]

[DOI]

CoRR, 2023

Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation.

[BibT_eX]

[DOI]

Sathyawageeswar Subramanian

Satoshi Hayakawa

Proceedings of the International Conference on Machine Learning, 2023

How Powerful are Shallow Neural Networks with Bandlimited Random Weights?

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

2022

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

[BibT_eX]

[DOI]

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.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

2021

Exponential Error Convergence in Data Classification with Optimized Random Features: Acceleration by Quantum Machine Learning.

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

CoRR, 2021

Differentiable Multiple Shooting Layers.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

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

[BibT_eX]

[DOI]

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

2020

On the Approximation Lower Bound for Neural Nets with Random Weights.

[BibT_eX]

[DOI]

CoRR, 2020

Gradient Descent Converges to Ridgelet Spectrum.

[BibT_eX]

[DOI]

CoRR, 2020

Fast Quantum Algorithm for Learning with Optimized Random Features.

[BibT_eX]

[DOI]

Sathyawageeswar Subramanian

Masato Koashi

CoRR, 2020

Learning with Optimized Random Features: Exponential Speedup by Quantum Machine Learning without Sparsity and Low-Rank Assumptions.

[BibT_eX]

[DOI]

Sathyawageeswar Subramanian

Masato Koashi

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

2019

Transport Analysis of Infinitely Deep Neural Network.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2019

Numerical Integration Method for Training Neural Network.

[BibT_eX]

[DOI]

CoRR, 2019

2018

EEG dipole source localization with information criteria for multiple particle filters.

[BibT_eX]

[DOI]

Neural Networks, 2018

Integral representation of the global minimizer.

[BibT_eX]

[DOI]

CoRR, 2018

Localizing Current Dipoles from EEG Data Using a Birth-Death Process.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine, 2018

2017

Transportation analysis of denoising autoencoders: a novel method for analyzing deep neural networks.

[BibT_eX]

[DOI]

CoRR, 2017

2016

Decoding Stacked Denoising Autoencoders.

[BibT_eX]

[DOI]

CoRR, 2016

2015

Neural Network with Unbounded Activations is Universal Approximator.

[BibT_eX]

[DOI]

CoRR, 2015

2014

Sampling Hidden Parameters from Oracle Distribution.

[BibT_eX]

[DOI]

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2014, 2014

2013

Nonparametric Weight Initialization of Neural Networks via Integral Representation.

[BibT_eX]

[DOI]