論文・研究業績
論文と関連資料へのリンクをまとめています。
ジャーナル論文
TMLR 2026 Generalization Measures under Controlled Covariate Shift: A Regime-Aware Benchmark
Transactions on Machine Learning Research, 2026年8月（採択済み）
TMLR 2026 What do near-optimal learning rate schedules look like?
Transactions on Machine Learning Research, 2026年6月
TMLR 2025 Pseudo-Asynchronous Local SGD: Robust and Efficient Data-Parallel Training
Transactions on Machine Learning Research, 2025年8月
TMLR 2025 An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration
Transactions on Machine Learning Research, 2025年4月
PRL Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration
Pattern Recognition Letters, 2025年2月
TMLR 2024 Towards Understanding Variants of Invariant Risk Minimization from the Perspective of Calibration
Transactions on Machine Learning Research, 2024年6月
TMLR 2023 Empirical Study on Optimizer Selection for Out-of-Distribution Generalizations
Transactions on Machine Learning Research, 2023年6月
国際会議論文
ICML 2026 Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
International Conference on Machine Learning, 2026年7月
ICLR 2026 On Fairness of Task Arithmetic: The Role of Task Vectors
International Conference on Learning Representations, 2026年1月
ICLR 2026 DiTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
International Conference on Learning Representations, 2026年1月
ICLR 2025 Mastering Task Arithmetic: τJp as a Key Indicator for Weight Disentanglement
International Conference on Learning Representations, 2025年4月
ICML 2024 No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths
International Conference on Machine Learning, 2024年7月
IJCNN 2023 How Image Corruption and Perturbation Affect Out-Of-Distribution Generalization and Calibration
International Joint Conference on Neural Networks, 2023年6月
AISTATS 2023 Conjugate Gradient Method for Generative Adversarial Networks
International Conference on Artificial Intelligence and Statistics, 2023年5月
CoLLAs 2022 Optimal Transport Meets Noisy Label Robust Loss and MixUp Regularization for Domain Adaptation
Conference on Lifelong Learning Agents, 2022年8月
HPC Asia 2018 Accelerating Convolutional Neural Networks Using Low Precision Arithmetic
International Conference on High Performance Computing in Asia-Pacific Region, 2018年1月
HPCS 2017 Accelerating Matrix Multiplication in Deep Learning by using Low-Rank Approximation
International Conference on High Performance Computing & Simulation, 2017年7月
プレプリント・査読中(7)
arXiv arXiv Under Review Orth-Dion: Eliminating Geometric Mismatch in Distributed Low-Rank Spectral Optimization
Under Review, 2026年5月（査読中）
Under Review Convergence Bound and Critical Batch Size of Muon Optimizer
Under Review, 2025年7月（査読中）
SSRN arXiv arXiv
ワークショップ論文(9)
ICLR 2026 Workshop The Geometry of Spectral Gradient Descent: Layerwise Criteria for SignSGD vs SpecSGD
ICLR 2026 Workshop on Geometry-grounded Representation Learning and Generative Modeling, 2026年2月
ICLR 2024 Workshop Smoothness-Adaptive Sharpness Aware Minimization for Finding Flatter Minima
ICLR 2024 Workshop on Practical ML for Low Resource Settings, 2024年5月
NarSUM 2023 Story-to-Images Translation: Leveraging Diffusion Models and Large Language Models for Sequence Image Generation
ACM Multimedia 2023 Workshop on User-centric Narrative Summarization of Long Videos, 2023年10月
UNCV 2023 On the Interplay of Curvature, Calibration and Out-of-Distribution Generalization: Insights from SAM and Focal Loss Analyses
ICCV 2023 Workshop on Uncertainty Quantification for Computer Vision, 2023年10月
ICLR 2023 Workshop Necessary and Sufficient Hypothesis of Curvature: Understanding Connection Between Out-of-Distribution Generalization and Calibration
ICLR 2023 Workshop on Domain Generalization, 2023年5月
MLSS 2020 Towards Understanding the Relationship of Batch Size and Iterations in Deep Learning
Machine Learning Summer School 2020, 2020年6月
ACML 2019 Workshop On Empirical Analysis of Layer-wise Learning Rate Schedule
Asian Conference on Machine Learning 2019 Workshop, 2019年11月
HPML 2019 A Performance Improvement Approach for Second-Order Optimization in Large Mini-batch Training
2nd High Performance Machine Learning Workshop, 2019年5月
Tokyo Tech-Stony Brook Joint Meeting Noise Injection Leads to Better Generalization in Large Mini-Batch Training
Tokyo Institute of Technology and Stony Brook University Joint Science and Technology Meeting, 2019年5月
同等貢献