Skip to content
conftrace_

Ryo Karakida

11 papers · 2019–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+3 more ↓ 🐣 Hot Topic Early Bird 🌍 Conference Polyglot Β· Bronze πŸƒ Academic Marathon Β· Sprint πŸ—ΊοΈ Taxonomy Completionist (17) πŸ† Keyword Champion (4)
πŸ’Ž Century Club Β· Bronze πŸ—ƒοΈ Keyword Collector (54) πŸ”₯ Unstoppable Β· Bronze

Venues

AISTATS (3) ICLR (3) ICML (3) NeurIPS (2)

Top co-authors

Shotaro Akaho (3) Tomohiro Hayase (3) Shun-ichi Amari (3) Kazuki Osawa (2) Satoki Ishikawa (2) Han Bao (1) Rio Yokota (1) Tomoumi Takase (1) Masafumi Oizumi (1) Ryuichiro Hataya (1)

Research topics

Machine Learning (11) Optimization & Theory Β· Machine Learning (11) Deep Learning (7) Architectures (5) Optimization & Theory Β· Deep Learning (3) Artificial Intelligence (2) Core Methods (2) Techniques (2) Core AI (1) Learning Paradigms (1) Learning Types (1)

Keywords

neural network optimization (5) fisher information matrix (4) maximal update parameterization (2) neural tangent kernel (2) deep neural network (2) batch normalization (1) transfer learning (1) catastrophic forgetting (1) deep learning (1) feature learning (1) loss landscape (1) natural gradient (1) fisher information (1) generalization error (1) generalization ability (1) hyperparameter transfer (1) natural gradient descent (1) finite difference (1) predictive coding (1) convergence analysis (1)

Papers

Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation ICLR 2025 On the Parameterization of Second-Order Optimization Effective towards the Infinite Width ICLR 2024 Self-attention Networks Localize When QK-eigenspectrum Concentrates ICML 2024 Understanding MLP-Mixer as a wide and sparse MLP ICML 2024 Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias ICML 2023 Learning curves for continual learning in neural networks: Self-knowledge transfer and forgetting ICLR 2022 The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry AISTATS 2021 Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks NeurIPS 2020 Fisher Information and Natural Gradient Learning in Random Deep Networks AISTATS 2019 The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks NeurIPS 2019 Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach AISTATS 2019