default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDRyo Karakida
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2025
[j8]Tomoumi Takase
, Ryo Karakida:
Optimal layer selection for latent data augmentation. Neural Networks 181: 106753 (2025)- 2024
- [c13]Satoki Ishikawa, Ryo Karakida:
On the Parameterization of Second-Order Optimization Effective towards the Infinite Width. ICLR 2024 - [c12]Han Bao, Ryuichiro Hataya, Ryo Karakida:
Self-attention Networks Localize When QK-eigenspectrum Concentrates. ICML 2024 - [c11]Tomohiro Hayase, Ryo Karakida:
Understanding MLP-Mixer as a wide and sparse MLP. ICML 2024 - [i19]Han Bao, Ryuichiro Hataya, Ryo Karakida:
Self-attention Networks Localize When QK-eigenspectrum Concentrates. CoRR abs/2402.02098 (2024) - [i18]Ryo Karakida, Toshihiro Ota, Masato Taki:
Hierarchical Associative Memory, Parallelized MLP-Mixer, and Symmetry Breaking. CoRR abs/2406.12220 (2024) - [i17]Tomoumi Takase, Ryo Karakida:
Optimal Layer Selection for Latent Data Augmentation. CoRR abs/2408.13426 (2024) - 2023
- [j7]Toshihiro Ota, Ryo Karakida:
Attention in a Family of Boltzmann Machines Emerging From Modern Hopfield Networks. Neural Comput. 35(8): 1463-1480 (2023) - [j6]Kaito Watanabe, Kotaro Sakamoto, Ryo Karakida, Sho Sonoda, Shun-ichi Amari:
Deep learning in random neural fields: Numerical experiments via neural tangent kernel. Neural Networks 160: 148-163 (2023) - [c10]Ryo Karakida, Tomoumi Takase, Tomohiro Hayase, Kazuki Osawa:
Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias. ICML 2023: 15809-15827 - [i16]Tomohiro Hayase, Ryo Karakida:
MLP-Mixer as a Wide and Sparse MLP. CoRR abs/2306.01470 (2023) - [i15]Satoki Ishikawa, Ryo Karakida:
On the Parameterization of Second-Order Optimization Effective Towards the Infinite Width. CoRR abs/2312.12226 (2023) - 2022
- [c9]Ryo Karakida, Shotaro Akaho:
Learning curves for continual learning in neural networks: Self-knowledge transfer and forgetting. ICLR 2022 - [i14]Kaito Watanabe, Kotaro Sakamoto, Ryo Karakida, Sho Sonoda, Shun-ichi Amari:
Deep Learning in Random Neural Fields: Numerical Experiments via Neural Tangent Kernel. CoRR abs/2202.05254 (2022) - [i13]Ryo Karakida, Tomoumi Takase, Tomohiro Hayase, Kazuki Osawa:
Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias. CoRR abs/2210.02720 (2022) - [i12]Toshihiro Ota, Ryo Karakida:
Attention in a family of Boltzmann machines emerging from modern Hopfield networks. CoRR abs/2212.04692 (2022) - 2021
- [j5]Tomoumi Takase, Ryo Karakida, Hideki Asoh:
Self-paced data augmentation for training neural networks. Neurocomputing 442: 296-306 (2021) - [j4]Ryo Karakida, Shotaro Akaho, Shun-ichi Amari:
Pathological Spectra of the Fisher Information Metric and Its Variants in Deep Neural Networks. Neural Comput. 33(8): 2274-2307 (2021) - [c8]Tomohiro Hayase, Ryo Karakida:
The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry. AISTATS 2021: 334-342 - [i11]Ryo Karakida, Shotaro Akaho:
Learning Curves for Sequential Training of Neural Networks: Self-Knowledge Transfer and Forgetting. CoRR abs/2112.01653 (2021) - 2020
- [c7]Ryo Karakida, Kazuki Osawa:
Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks. NeurIPS 2020 - [i10]Tomohiro Hayase, Ryo Karakida:
The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry. CoRR abs/2006.07814 (2020) - [i9]Ryo Karakida, Kazuki Osawa:
Understanding Approximate Fisher Information for Fast Convergence of Natural Gradient Descent in Wide Neural Networks. CoRR abs/2010.00879 (2020) - [i8]Tomoumi Takase, Ryo Karakida, Hideki Asoh:
Self-paced Data Augmentation for Training Neural Networks. CoRR abs/2010.15434 (2020)
2010 – 2019
- 2019
- [j3]Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi, Marco Cuturi:
Information Geometry for Regularized Optimal Transport and Barycenters of Patterns. Neural Comput. 31(5): 827-848 (2019) - [c6]Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi:
Fisher Information and Natural Gradient Learning in Random Deep Networks. AISTATS 2019: 694-702 - [c5]Ryo Karakida, Shotaro Akaho, Shun-ichi Amari:
Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach. AISTATS 2019: 1032-1041 - [c4]Ryo Karakida, Shotaro Akaho, Shun-ichi Amari:
The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks. NeurIPS 2019: 6403-6413 - [i7]Ryo Karakida, Shotaro Akaho, Shun-ichi Amari:
The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks. CoRR abs/1906.02926 (2019) - [i6]Ryo Karakida, Shotaro Akaho, Shun-ichi Amari:
Pathological spectra of the Fisher information metric and its variants in deep neural networks. CoRR abs/1910.05992 (2019) - 2018
- [j2]Shun-ichi Amari, Tomoko Ozeki, Ryo Karakida, Yuki Yoshida, Masato Okada:
Dynamics of Learning in MLP: Natural Gradient and Singularity Revisited. Neural Comput. 30(1) (2018) - [i5]Ryo Karakida, Shotaro Akaho, Shun-ichi Amari:
Universal Statistics of Fisher Information in Deep Neural Networks: Mean Field Approach. CoRR abs/1806.01316 (2018) - [i4]Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi:
Statistical Neurodynamics of Deep Networks: Geometry of Signal Spaces. CoRR abs/1808.07169 (2018) - [i3]Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi:
Fisher Information and Natural Gradient Learning of Random Deep Networks. CoRR abs/1808.07172 (2018) - 2017
- [c3]Ryo Karakida, Shun-ichi Amari:
Information Geometry of Wasserstein Divergence. GSI 2017: 119-126 - [i2]Shun-ichi Amari, Ryo Karakida, Masafumi Oizumi:
Information Geometry Connecting Wasserstein Distance and Kullback-Leibler Divergence via the Entropy-Relaxed Transportation Problem. CoRR abs/1709.10219 (2017) - [i1]Yoshihiro Nagano, Ryo Karakida, Masato Okada:
Concept Formation and Dynamics of Repeated Inference in Deep Generative Models. CoRR abs/1712.04195 (2017) - 2016
- [j1]Ryo Karakida, Masato Okada, Shun-ichi Amari:
Dynamical analysis of contrastive divergence learning: Restricted Boltzmann machines with Gaussian visible units. Neural Networks 79: 78-87 (2016) - [c2]Ryo Karakida, Masato Okada, Shun-ichi Amari:
Maximum likelihood learning of RBMs with Gaussian visible units on the Stiefel manifold. ESANN 2016 - [c1]Ryo Karakida, Masato Okada, Shun-ichi Amari:
Adaptive Natural Gradient Learning Algorithms for Unnormalized Statistical Models. ICANN (1) 2016: 427-434
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-10-23 20:32 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
