Masahiro Ikeda

Joined

July 2019

Names

Masahiro Ikeda

Emails

****@riken.jp (Confirmed)

,

****@gmail.com (Confirmed)

,

****@ist.osaka-u.ac.jp (Confirmed)

Personal Links

Career & Education History

Researcher

RIKEN (riken.jp)

2017 – 2025

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs
Yuka Hashimoto, Sho Sonoda, Isao Ishikawa, Masahiro Ikeda
- ICLR 2026 Poster
- Readers: Everyone
Why and When Deep is Better than Shallow: An Implementation-Agnostic State-Transition View of Depth Supremacy
Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda
- Submitted to ICLR 2026
- Readers: Everyone
Deep Ridgelet Transform and Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines
Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda
- ICML 2025 poster
- Readers: Everyone
Unified Universality Theorem for Deep and Shallow Joint-Group-Equivariant Machines
Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda
- Submitted to ICLR 2025
- Readers: Everyone
Spectral Truncation Kernels: Noncommutativity in $C^*$-algebraic Kernel Machines
Yuka Hashimoto, Ayoub Hafid, Masahiro Ikeda, Hachem Kadri
- Submitted to ICLR 2025
- Readers: Everyone
Constructive Universal Approximation Theorems for Deep Joint-Equivariant Networks by Schur's Lemma
Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda
- Submitted to NeurIPS 2024
- Readers: Everyone
Position: $C^*$-Algebraic Machine Learning $-$ Moving in a New Direction
Yuka Hashimoto, Masahiro Ikeda, Hachem Kadri
- ICML 2024 Poster
- Readers: Everyone
Koopman Spectrum Nonlinear Regulators and Efficient Online Learning
Motoya Ohnishi, Isao Ishikawa, Kendall Lowrey, Masahiro Ikeda, Sham M. Kakade, Yoshinobu Kawahara
- Accepted by TMLR
- Readers: Everyone
Dynamic Structure Estimation from Bandit Feedback using Nonvanishing Exponential Sums
Motoya Ohnishi, Isao Ishikawa, Yuko Kuroki, Masahiro Ikeda
- Accepted by TMLR
- Readers: Everyone
Deep Ridgelet Transform: Voice with Koopman Operator Constructively Proves Universality of Formal Deep Networks
Sho Sonoda, Yuka Hashimoto, Isao Ishikawa, Masahiro Ikeda
- NeurReps 2023 Poster
- Readers: Everyone

View all 17 publications

Co-Authors