Ryo Karakida - RankMe

48 papers A* 8A 3B 1Journal 33Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	The Impact of Anisotropic Covariance Structure on the Training Dynamics and Generalization Error of Linear Networks. CoRR Taishi Watanabe, Ryo Karakida, Jun-nosuke Teramae
2025	J	`jnl`	Continual learning in inertial measurement unit-based human activity recognition with user-centric class-incremental learning scenario. Expert Syst. Appl. Suguru Kanoga, Yuya Tsukiji, Ryo Karakida
2025	J	`jnl`	Gaussian Equivalence for Self-Attention: Asymptotic Spectral Analysis of Attention Matrix. CoRR Tomohiro Hayase, Benoit Collins, Ryo Karakida
2025	J	`jnl`	Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs. CoRR Mana Sakai, Ryo Karakida, Masaaki Imaizumi
2025	A*	`conf`	Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation. ICLR Satoki Ishikawa, Rio Yokota, Ryo Karakida
2025	J	`jnl`	Optimal layer selection for latent data augmentation. Neural Networks Tomoumi Takase, Ryo Karakida
2025	J	`jnl`	Recurrent Self-Attention Dynamics: An Energy-Agnostic Perspective from Jacobians. CoRR Akiyoshi Tomihari, Ryo Karakida
2024	—	`conf`	Deep Generative Replay-based Class-incremental Continual Learning in sEMG-based Pattern Recognition. EMBC Suguru Kanoga, Ryo Karakida, Takayuki Hoshino, Yuto Okawa, Mitsunori Tada
2024	J	`jnl`	Hierarchical Associative Memory, Parallelized MLP-Mixer, and Symmetry Breaking. CoRR Ryo Karakida, Toshihiro Ota, Masato Taki
2024	J	`jnl`	Local Loss Optimization in the Infinite Width: Stable Parameterization of Predictive Coding Networks and Target Propagation. CoRR Satoki Ishikawa, Rio Yokota, Ryo Karakida
2024	A*	`conf`	On the Parameterization of Second-Order Optimization Effective towards the Infinite Width. ICLR Satoki Ishikawa, Ryo Karakida
2024	J	`jnl`	Optimal Layer Selection for Latent Data Augmentation. CoRR Tomoumi Takase, Ryo Karakida
2024	A*	`conf`	Self-attention Networks Localize When QK-eigenspectrum Concentrates. ICML Han Bao, Ryuichiro Hataya, Ryo Karakida
2024	J	`jnl`	Self-attention Networks Localize When QK-eigenspectrum Concentrates. CoRR Han Bao, Ryuichiro Hataya, Ryo Karakida
2024	A*	`conf`	Understanding MLP-Mixer as a wide and sparse MLP. ICML Tomohiro Hayase, Ryo Karakida
2023	J	`jnl`	Attention in a Family of Boltzmann Machines Emerging From Modern Hopfield Networks. Neural Comput. Toshihiro Ota, Ryo Karakida
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	J	`jnl`	MLP-Mixer as a Wide and Sparse MLP. CoRR Tomohiro Hayase, Ryo Karakida
2023	J	`jnl`	On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width. CoRR Satoki Ishikawa, Ryo Karakida
2023	A*	`conf`	Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias. ICML Ryo Karakida, Tomoumi Takase, Tomohiro Hayase, Kazuki Osawa
2022	J	`jnl`	Attention in a family of Boltzmann machines emerging from modern Hopfield networks. CoRR Toshihiro Ota, Ryo Karakida
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`	Learning curves for continual learning in neural networks: Self-knowledge transfer and forgetting. ICLR Ryo Karakida, Shotaro Akaho
2022	J	`jnl`	Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias. CoRR Ryo Karakida, Tomoumi Takase, Tomohiro Hayase, Kazuki Osawa
2021	J	`jnl`	Learning Curves for Sequential Training of Neural Networks: Self-Knowledge Transfer and Forgetting. CoRR Ryo Karakida, Shotaro Akaho
2021	J	`jnl`	Pathological Spectra of the Fisher Information Metric and Its Variants in Deep Neural Networks. Neural Comput. Ryo Karakida, Shotaro Akaho, Shun-ichi Amari
2021	J	`jnl`	Self-paced data augmentation for training neural networks. Neurocomputing Tomoumi Takase, Ryo Karakida, Hideki Asoh
2021	A	`conf`	The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry. AISTATS Tomohiro Hayase, Ryo Karakida
2020	J	`jnl`	Self-paced Data Augmentation for Training Neural Networks. CoRR Tomoumi Takase, Ryo Karakida, Hideki Asoh
2020	J	`jnl`	The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry. CoRR Tomohiro Hayase, Ryo Karakida
2020	A*	`conf`	Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks. NeurIPS Ryo Karakida, Kazuki Osawa
2020	J	`jnl`	Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks. CoRR Ryo Karakida, Kazuki Osawa
2019	A	`conf`	Fisher Information and Natural Gradient Learning in Random Deep Networks. AISTATS Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi
2019	J	`jnl`	Information Geometry for Regularized Optimal Transport and Barycenters of Patterns. Neural Comput. Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi, Marco Cuturi
2019	J	`jnl`	Pathological spectra of the Fisher information metric and its variants in deep neural networks. CoRR Ryo Karakida, Shotaro Akaho, Shun-ichi Amari
2019	A*	`conf`	The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks. NeurIPS Ryo Karakida, Shotaro Akaho, Shun-ichi Amari
2019	J	`jnl`	The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks. CoRR Ryo Karakida, Shotaro Akaho, Shun-ichi Amari
2019	A	`conf`	Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach. AISTATS Ryo Karakida, Shotaro Akaho, Shun-ichi Amari
2018	J	`jnl`	Dynamics of Learning in MLP: Natural Gradient and Singularity Revisited. Neural Comput. Shun-ichi Amari, Tomoko Ozeki, Ryo Karakida, Yuki Yoshida, Masato Okada
2018	J	`jnl`	Fisher Information and Natural Gradient Learning of Random Deep Networks. CoRR Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi
2018	J	`jnl`	Statistical Neurodynamics of Deep Networks: Geometry of Signal Spaces. CoRR Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi
2018	J	`jnl`	Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach. CoRR Ryo Karakida, Shotaro Akaho, Shun-ichi Amari
2017	J	`jnl`	Concept Formation and Dynamics of Repeated Inference in Deep Generative Models. CoRR Yoshihiro Nagano, Ryo Karakida, Masato Okada
2017	J	`jnl`	Information Geometry Connecting Wasserstein Distance and Kullback-Leibler Divergence via the Entropy-Relaxed Transportation Problem. CoRR Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi
2017	—	`conf`	Information Geometry of Wasserstein Divergence. GSI Ryo Karakida, Shun-ichi Amari
2016	—	`conf`	Adaptive Natural Gradient Learning Algorithms for Unnormalized Statistical Models. ICANN (1) Ryo Karakida, Masato Okada, Shun-ichi Amari
2016	J	`jnl`	Dynamical analysis of contrastive divergence learning: Restricted Boltzmann machines with Gaussian visible units. Neural Networks Ryo Karakida, Masato Okada, Shun-ichi Amari
2016	B	`conf`	Maximum likelihood learning of RBMs with Gaussian visible units on the Stiefel manifold. ESANN Ryo Karakida, Masato Okada, Shun-ichi Amari