Accelerating matrix multiplication in deep learning by using low-rank approximation K Osawa, A Sekiya, H Naganuma, R Yokota 2017 International Conference on High Performance Computing & Simulation …, 2017 | 24 | 2017 |
Empirical Study on Optimizer Selection for Out-of-Distribution Generalization Hiroki Naganuma, Kartik Ahuj, Shiro Takag, Tetsuya Motokawa, Rio Yokota ... Transactions on Machine Learning Research, 2023 | 9* | 2023 |
Optimal transport meets noisy label robust loss and mixup regularization for domain adaptation K Fatras, H Naganuma, I Mitliagkas Conference on Lifelong Learning Agents, 966-981, 2022 | 5 | 2022 |
A Performance Improvement Approach for Second-Order Optimization in Large Mini-batch Training H Naganuma, R Yokota CCGRID 2019, 696-703, 2019 | 5 | 2019 |
Accelerating Convolutional Neural Networks Using Low Precision Arithmetic H Naganuma, R Yokota HPC Asia 2018, 2018 | 5 | 2018 |
An Empirical Investigation of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration H Naganuma, R Hataya, I Mitliagkas arXiv preprint arXiv:2307.08187, 2023 | 3 | 2023 |
Necessary and Sufficient Hypothesis of Curvature: Understanding Connection Between Out-of-Distribution Generalization and Calibration H Naganuma, M Kimura ICLR2023 Workshop on Domain Generalization, 2023 | 3 | 2023 |
低ランク近似を用いた深層学習の行列積の高速化 関谷翠, 大沢和樹, 長沼大樹, 横田理央 研究報告ハイパフォーマンスコンピューティング (HPC) 2017 (24), 1-7, 2017 | 3 | 2017 |
Augmenting NER Datasets with LLMs: Towards Automated and Refined Annotation Y Naraki, R Yamaki, Y Ikeda, T Horie, H Naganuma arXiv preprint arXiv:2404.01334, 2024 | 1 | 2024 |
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths C Guille-Escuret, H Naganuma, K Fatras, I Mitliagkas arXiv preprint arXiv:2306.11922, 2023 | 1 | 2023 |
Conjugate Gradient Method for Generative Adversarial Networks H Naganuma, H Iiduka International Conference on Artificial Intelligence and Statistics, 4381-4408, 2023 | 1 | 2023 |
How Image Corruption and Perturbation Affect Out-Of-Distribution Generalization and Calibration K Tada, H Naganuma International Joint Conference on Neural Networks (IJCNN 2023), 2023 | 1 | 2023 |
Design of a Smart Pacifier to Detect Dehydration in Babies and Shaping Parents' Behavior M SUGIMOTO, E YAMATSUTA, H NAGANUMA, R ARAKAWA, Y USHIRO, ... TSUKUBA GLOBAL SCIENCE WEEK 2018 ART & DESIGN SESSION PROCEEDINGS, 35-38, 2018 | 1 | 2018 |
Smoothness-Adaptive Sharpness-Aware Minimization for Finding Flatter Minima H Naganuma, JL Kim, A Kyrillidis, I Mitliagkas 5th Workshop on practical ML for limited/low resource settings, 2024 | | 2024 |
Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration M Kimura, H Naganuma arXiv preprint arXiv:2405.00442, 2024 | | 2024 |
Towards Understanding Variants of Invariant Risk Minimization through the Lens of Calibration K Yoshida, H Naganuma Transactions on Machine Learning Research, 2024 | | 2024 |
A Survey on Product Placement Strategies: Evaluating Effectiveness and Persuasion Resistance L Fujima, Y Mamiya, H Naganuma Available at SSRN 4649030, 2023 | | 2023 |
Story-to-Images Translation: Leveraging Diffusion Models and Large Language Models for Sequence Image Generation H Kumagai, R Yamaki, H Naganuma Proceedings of the 2nd Workshop on User-centric Narrative Summarization of …, 2023 | | 2023 |
On the Interplay of Curvature, Calibration and Out-of-Distribution Generalization: Insights from SAM and Focal Loss Analyses H Naganuma, M Kimura | | 2023 |
Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime H Naganuma, T Suzuki, R Yokota, M Nomura, K Ishikawa, I Sato | | 2021 |