Sho Sonoda - RankMe

45 papers A* 8A 1C 1Journal 33Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Don't Eliminate Cut: Exponential Separations in LLM-Based Theorem Proving. CoRR Sho Sonoda, Shunta Akiyama, Yuya Uezato
2026	J	`jnl`	Why Agentic Theorem Prover Works: A Statistical Provability Theory of Mathematical Reasoning Models. CoRR Sho Sonoda, Shunta Akiyama, Yuya Uezato
2025	A*	`conf`	Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines. ICML Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda
2025	J	`jnl`	Discovering New Theorems via LLMs with In-Context Proof Learning in Lean. CoRR Kazumi Kasaura, Naoto Onda, Yuta Oriike, Masaya Taniguchi, Akiyoshi Sannai, Sho Sonoda
2025	J	`jnl`	Generalization Through Growth: Hidden Dynamics Controls Depth Dependence. CoRR Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda
2025	J	`jnl`	Lean Formalization of Generalization Error Bound by Rademacher Complexity. CoRR Sho Sonoda, Kazumi Kasaura, Yuma Mizuno, Kei Tsukamoto, Naoto Onda
2025	J	`jnl`	LeanConjecturer: Automatic Generation of Mathematical Conjectures for Theorem Proving. CoRR Naoto Onda, Kazumi Kasaura, Yuta Oriike, Masaya Taniguchi, Akiyoshi Sannai, Sho Sonoda
2025	J	`jnl`	Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs. CoRR Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Masahiro Ikeda
2024	J	`jnl`	A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees. CoRR Toshinori Kitamura, Tadashi Kozuno, Masahiro Kato, Yuki Ichihara, Soichiro Nishimori, Akiyoshi Sannai, Sho Sonoda, Wataru Kumagai, Yutaka Matsuo
2024	J	`jnl`	A unified Fourier slice method to derive ridgelet transform for a variety of depth-2 neural networks. CoRR Sho Sonoda, Isao Ishikawa, Masahiro Ikeda
2024	J	`jnl`	Constructive Universal Approximation Theorems for Deep Joint-Equivariant Networks by Schur's Lemma. CoRR Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda
2024	A*	`conf`	Koopman-based generalization bound: New aspect for full-rank weights. ICLR Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Atsushi Nitanda, Taiji Suzuki
2023	J	`jnl`	Deep Ridgelet Transform: Voice with Koopman Operator Proves Universality of Formal Deep Networks. CoRR Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda
2023	J	`jnl`	Deep learning in random neural fields: Numerical experiments via neural tangent kernel. Neural Networks Kaito Watanabe, Kotaro Sakamoto, Ryo Karakida, Sho Sonoda, Shun-ichi Amari
2023	A*	`conf`	How Powerful are Shallow Neural Networks with Bandlimited Random Weights? ICML Ming Li, Sho Sonoda, Feilong Cao, Yu Guang Wang, Jiye Liang
2023	—	`conf`	Joint Group Invariant Functions on Data-Parameter Domain Induce Universal Neural Networks. NeurReps Sho Sonoda, Hideyuki Ishi, Isao Ishikawa, Masahiro Ikeda
2023	J	`jnl`	Joint Group Invariant Functions on Data-Parameter Domain Induce Universal Neural Networks. CoRR Sho Sonoda, Hideyuki Ishi, Isao Ishikawa, Masahiro Ikeda
2023	J	`jnl`	Koopman-Based Bound for Generalization: New Aspect of Neural Networks Regarding Nonlinear Noise Filtering. CoRR Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Atsushi Nitanda, Taiji Suzuki
2023	J	`jnl`	LPML: LLM-Prompting Markup Language for Mathematical Reasoning. CoRR Ryutaro Yamauchi, Sho Sonoda, Akiyoshi Sannai, Wataru Kumagai
2023	A*	`conf`	Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation. ICML Hayata Yamasaki, Sathyawageeswar Subramanian, Satoshi Hayakawa, Sho Sonoda
2023	J	`jnl`	Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation. CoRR Hayata Yamasaki, Sathyawageeswar Subramanian, Satoshi Hayakawa, Sho Sonoda
2022	J	`jnl`	Deep Learning in Random Neural Fields: Numerical Experiments via Neural Tangent Kernel. CoRR Kaito Watanabe, Kotaro Sakamoto, Ryo Karakida, Sho Sonoda, Shun-ichi Amari
2022	A*	`conf`	Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis. ICML Sho Sonoda, Isao Ishikawa, Masahiro Ikeda
2022	J	`jnl`	Fully-Connected Network on Noncompact Symmetric Space and Ridgelet Transform based on Helgason-Fourier Analysis. CoRR Sho Sonoda, Isao Ishikawa, Masahiro Ikeda
2022	A*	`conf`	Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups. NeurIPS Sho Sonoda, Isao Ishikawa, Masahiro Ikeda
2022	J	`jnl`	Universality of group convolutional neural networks based on ridgelet analysis on groups. CoRR Sho Sonoda, Isao Ishikawa, Masahiro Ikeda
2021	A*	`conf`	Differentiable Multiple Shooting Layers. NeurIPS Stefano Massaroli, Michael Poli, Sho Sonoda, Taiji Suzuki, Jinkyoo Park, Atsushi Yamashita, Hajime Asama
2021	J	`jnl`	Differentiable Multiple Shooting Layers. CoRR Stefano Massaroli, Michael Poli, Sho Sonoda, Taiji Suzuki, Jinkyoo Park, Atsushi Yamashita, Hajime Asama
2021	J	`jnl`	Exponential Error Convergence in Data Classification with Optimized Random Features: Acceleration by Quantum Machine Learning. CoRR Hayata Yamasaki, Sho Sonoda
2021	J	`jnl`	Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null Space. CoRR Sho Sonoda, Isao Ishikawa, Masahiro Ikeda
2021	A	`conf`	Ridge Regression with Over-parametrized Two-Layer Networks Converge to Ridgelet Spectrum. AISTATS Sho Sonoda, Isao Ishikawa, Masahiro Ikeda
2020	J	`jnl`	Fast Quantum Algorithm for Learning with Optimized Random Features. CoRR Hayata Yamasaki, Sathyawageeswar Subramanian, Sho Sonoda, Masato Koashi
2020	J	`jnl`	Gradient Descent Converges to Ridgelet Spectrum. CoRR Sho Sonoda, Isao Ishikawa, Masahiro Ikeda
2020	A*	`conf`	Learning with Optimized Random Features: Exponential Speedup by Quantum Machine Learning without Sparsity and Low-Rank Assumptions. NeurIPS Hayata Yamasaki, Sathyawageeswar Subramanian, Sho Sonoda, Masato Koashi
2020	J	`jnl`	On the Approximation Lower Bound for Neural Nets with Random Weights. CoRR Sho Sonoda, Ming Li, Feilong Cao, Changqin Huang, Yu Guang Wang
2019	J	`jnl`	Numerical Integration Method for Training Neural Network. CoRR Sho Sonoda
2019	J	`jnl`	Transport Analysis of Infinitely Deep Neural Network. J. Mach. Learn. Res. Sho Sonoda, Noboru Murata
2018	J	`jnl`	EEG dipole source localization with information criteria for multiple particle filters. Neural Networks Sho Sonoda, Keita Nakamura, Yuki Kaneda, Hideitsu Hino, Shotaro Akaho, Noboru Murata, Eri Miyauchi, Masahiro Kawasaki
2018	J	`jnl`	Integral representation of the global minimizer. CoRR Sho Sonoda, Isao Ishikawa, Masahiro Ikeda, Kei Hagihara, Yoshihiro Sawano, Takuo Matsubara, Noboru Murata
2018	—	`conf`	Localizing Current Dipoles from EEG Data Using a Birth-Death Process. BIBM Keita Nakamura, Sho Sonoda, Hideitsu Hino, Masahiro Kawasaki, Shotaro Akaho, Noboru Murata
2017	J	`jnl`	Transportation analysis of denoising autoencoders: a novel method for analyzing deep neural networks. CoRR Sho Sonoda, Noboru Murata
2016	J	`jnl`	Decoding Stacked Denoising Autoencoders. CoRR Sho Sonoda, Noboru Murata
2015	J	`jnl`	Neural Network with Unbounded Activations is Universal Approximator. CoRR Sho Sonoda, Noboru Murata
2014	C	`conf`	Sampling Hidden Parameters from Oracle Distribution. ICANN Sho Sonoda, Noboru Murata
2013	J	`jnl`	Nonparametric Weight Initialization of Neural Networks via Integral Representation. CoRR Sho Sonoda, Noboru Murata