Karakida, Ryo

13 publications

NeurIPS 2025 Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs Mana Sakai, Ryo Karakida, Masaaki Imaizumi

ICLR 2025 Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation Satoki Ishikawa, Rio Yokota, Ryo Karakida

NeurIPS 2025 Recurrent Self-Attention Dynamics: An Energy-Agnostic Perspective from Jacobians Akiyoshi Tomihari, Ryo Karakida

ICLR 2024 On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width Satoki Ishikawa, Ryo Karakida

ICML 2024 Self-Attention Networks Localize When QK-Eigenspectrum Concentrates Han Bao, Ryuichiro Hataya, Ryo Karakida

ICML 2024 Understanding MLP-Mixer as a Wide and Sparse MLP Tomohiro Hayase, Ryo Karakida

ICML 2023 Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias Ryo Karakida, Tomoumi Takase, Tomohiro Hayase, Kazuki Osawa

ICLR 2022 Learning Curves for Continual Learning in Neural Networks: Self-Knowledge Transfer and Forgetting Ryo Karakida, Shotaro Akaho

AISTATS 2021 The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry Tomohiro Hayase, Ryo Karakida

NeurIPS 2020 Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks Ryo Karakida, Kazuki Osawa

AISTATS 2019 Fisher Information and Natural Gradient Learning in Random Deep Networks Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi

NeurIPS 2019 The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks Ryo Karakida, Shotaro Akaho, Shun-ichi Amari

AISTATS 2019 Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach Ryo Karakida, Shotaro Akaho, Shun-ichi Amari