研究室のページ（日本語）はこちら
#Papers
#InReview
-
Outlier-robust neural network training: variation regularization meets trimmed loss to prevent functional breakdown
arXiv: October 2024
under review
https://doi.org/10.48550/arXiv.2308.02293
Two authors (Okuno and Yagishita) contributed equally to this work. This manuscript is a complete rewrite of the earlier preprint HOVR (arXiv:2308.02293v2), which was released in August 2023 (unpublished and not intended for future publication), with the addition of new authors and the introduction of new techniques. Please note that arXiv versions v3 and beyond refer to this manuscript as an update to the earlier versions (v1 and v2).
-
An integrated perspective of robustness in regression through the lens of the bias-variance trade-off
arXiv: July 2024
in preparation for submission
-
A multivariate adaptation of direct kernel estimation of density ratio
arXiv: November 2023
in preparation for resubmission
#Journal
-
A Greedy and Optimistic Clustering for Leveraging Individual Covariate Uncertainty
Annals of the Institute of Statistical Mathematics
2025
accepted
-
A Systematic Approach to Decomposing Numerical Turbulence Fields into Substructures
Physics of Plasmas
2025
https://doi.org/10.1063/5.0256907
(Data and Code) https://doi.org/10.5281/zenodo.14868307
-
Minimizing robust density power-based divergences for general parametric density models
Annals of the Institute of Statistical Mathematics
2024
https://doi.org/10.1007/s10463-024-00906-9
Video in English and in Japanese
R package: oknakfm/sgdpd, パッケージ解説動画 (日本語)
-
An interpretable neural network-based non-proportional odds model for ordinal regression
Journal of Computational and Graphical Statistics
2024
-
Autoregressive with Slack Time Series Model for Forecasting a Partially-Observed Dynamical Time Series
IEEE Access
2024
-
Minimax Analysis for Inverse Risk in Nonparametric Planer Invertible Regression
Electronic Journal of Statistics
2024
-
A generalization gap estimation for overparameterized models via the Langevin functional variance
Journal of Computational and Graphical Statistics
2023
https://doi.org/10.1080/10618600.2023.2197488
-
Finding r-II sibling stars in the Milky Way with the Greedy Optimistic Clustering algorithm
Astrophysical Journal
2023
-
Dependence of variance on covariate design in nonparametric link regression
Statistics and Probability Letters
2023
-
Hyperlink Regression via Bregman Divergence
Neural Networks
2020
#Conference
-
Extrapolation Towards Imaginary 0-Nearest Neighbour and Its Improved Convergence Rate
Advances in Neural Information Processing Systems (NeurIPS)
2020
https://papers.nips.cc/paper/2020/hash/f9028faec74be6ec9b852b0a542e2f39-Abstract.html
-
Representation Learning with Weighted Inner Product for Universal Approximation of General Similarities
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI)
2019
-
Robust Graph Embedding with Noisy Link Weights
22nd International Conference on Artificial Intelligence and Statistics (AISTATS)
2019
-
Graph Embedding with Shifted Inner Product Similarity and Its Improved Approximation Capability
22nd International Conference on Artificial Intelligence and Statistics (AISTATS)
2019
-
A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks
35th International Conference on Machine Learning (ICML)
2018
-
Image and tag retrieval by leveraging image-group links with multi-domain graph embeddings
Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP)
2016
#MinorWorks
-
Hierarchical Clustering of Modes in Numerical Turbulence Fields
Plasma and Fusion Research: Rapid Communications
2024
-
On representation power of neural network-based graph embedding and beyond
ICML 2018 workshop on Theoretical Foundations and Applications of Deep Generative Models (TADGM)
2018
-
Deep Multi-view Representation Learning Based on Adaptive Weighted Similarity
International Workshop on Symbolic-Neural Learning (SNL)
2017
#Shelved
*No plans for future publication. Left as is.-
A stochastic optimization approach to train non-linear neural networks with regularization of higher-order total variation
arXiv: August 2023
It has been incorporated into the newer ARTL manuscript and will not be published in the future. Left as is
https://arxiv.org/abs/2308.02293v2
Video in English and in Japanese
This manuscript has been completely rewritten as a new manuscript, ARTL, with the addition of new authors and the introduction of new techniques. Namely, the HOVR manuscript (arXiv v1 and v2) has been incorporated into the ARTL manuscript (arXiv versions v3 and beyond).
-
Improving Nonparametric Classification via Local Radial Regression with an Application to Stock Prediction
arXiv: December 2021
Left as is
https://doi.org/10.48550/arXiv.2112.13951
First two authors (Cao and Okuno) contributed equally to this work.
-
Stochastic Neighbor Embedding of Multimodal Relational Data for Image-Text Simultaneous Visualization
arXiv: May 2020
Left as is
#論文解説
-
論文解説：貪欲かつ楽観的なクラスタリングと天文データへの応用
Jxiv
2025
-
論文解説：プラズマ乱流の分解
Jxiv
2025
-
論文解説：仮想的な0近傍法による高次バイアス補正
Jxiv
2024
-
論文解説：外れ値にロバストなニューラルネットの学習
Jxiv
2024
-
論文解説：一般の確率モデルでの冪密度ダイバージェンス最小化
Jxiv
2024
-
論文解説：可逆関数推定の難しさ - 生成モデルを念頭に
Jxiv
2024
-
論文解説：順序回帰における柔軟性とドメイン制約のトレードオフ
Jxiv
2023
-
論文解説：WAIC による過剰パラメータモデルの汎化誤差推定
Jxiv
2023
#国内論文/レター
-
予測モデルの可逆性について
日本統計学会誌
2025
https://doi.org/10.11329/jjssj.54.205
小川研究奨励賞特別寄稿論文．
-
マルチスケールk-近傍法における回帰関数および損失関数の検討
人工知能学会全国大会論文集
2021
-
マルチスケールk-近傍法による画像のExtreme Multi-Label分類
人工知能学会全国大会論文集
2021
-
グラフと近傍グラフの確率的同時埋め込みを用いたマルチモーダル関連性データの可視化
人工知能学会全国大会論文集
2020
-
擬ユークリッド空間への単語埋め込み
言語処理学会第25回年次大会論文集
2019
http://www.anlp.jp/proceedings/annual_meeting/2019/pdf_dir/P7-4.pdf
-
マッチング相関分析を用いた画像-マルチタグ間の相互検索
電子情報通信学会和文論文誌D: 研究速報(レター)
2016
#Awards
- Ogawa Research Award, Japan Statistical Society, 2024.
- Excellent Presentation Award (in the top 3~6/200), IBIS2023, 2023.
- Excellent Presentation Award (in the top 5~7/238), IBIS2019, 2019.
- Excellent Research Award, ICT-13@Kyoto University, 2019.
#Social
- Organizer of the planned session "Statistical Approaches in Various Sciences" in the spring meeting of the Japan Statistical Society (2025).
- PC member of the ISM-ISI-ISSAS Joint Conference (2025).
- Organizer of Workshop on Interdisciplinary Statistical Analysis with Computational Techniques 2025 (ISACT2025).
- Organizer of Fusion Plasma Workshop in the Japanese Joint Statistical Meeting 2024.
- SOC member of Data Oriented Astronomy 2024 (DOA2024).
- PC member of Symbolic Neural Learning 2024 (SNL2024).
- PC member of IBIS2022.
- A member of deep Jinbo-cho study group.
- A regular member of the Japan Statistical Society.
[Conference]
AISTATS (2019, 2021, 2025), ICML (2019-2022), ACML (2019, 2021, 2023), AAAI (2020), IJCAI (2022), BMVC (2020), NeurIPS (2020, 2024), UAI (2024), ISITA (2024).
[Journal]
Machine Learning,
Neural Networks,
Electronic Journal of Statistics,
Japanese Journal of Statistics and Data Science,
Statistics and Computing,
Annals of the Institute of Statistical Mathematics,
Annals of Data Science,
Advanced Robotics.