Hiroki Naganuma

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 16

Top Topics

Image Generation

Risk Minimization

Top Venues

Trans. Mach. Learn. Res.

Publications

Yuji Naraki, Ryosuke Yamaki, Yoshikazu Ikeda, Takafumi Horie, Hiroki Naganuma
Augmenting NER Datasets with LLMs: Towards Automated and Refined Annotation. CoRR (2024)
Kotaro Yoshida, Hiroki Naganuma
Towards Understanding Variants of Invariant Risk Minimization through the Lens of Calibration. CoRR (2024)
Kotaro Yoshida, Hiroki Naganuma
Towards Understanding Variants of Invariant Risk Minimization through the Lens of Calibration. Trans. Mach. Learn. Res. 2024 (2024)
Masanari Kimura, Hiroki Naganuma
Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration. CoRR (2024)
Hiroki Naganuma, Kartik Ahuja, Shiro Takagi, Tetsuya Motokawa, Rio Yokota, Kohta Ishikawa, Ikuro Sato, Ioannis Mitliagkas
Empirical Study on Optimizer Selection for Out-of-Distribution Generalization. Trans. Mach. Learn. Res. 2023 (2023)
Charles Guille-Escuret, Hiroki Naganuma, Kilian Fatras, Ioannis Mitliagkas
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths. CoRR (2023)
Haruka Kumagai, Ryosuke Yamaki, Hiroki Naganuma
Story-to-Images Translation: Leveraging Diffusion Models and Large Language Models for Sequence Image Generation. NarSUM@MM (2023)
Hiroki Naganuma, Hideaki Iiduka
Conjugate Gradient Method for Generative Adversarial Networks. AISTATS (2023)
Hiroki Naganuma, Ryuichiro Hataya
An Empirical Investigation of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration. CoRR (2023)
Keigo Tada, Hiroki Naganuma
How Image Corruption and Perturbation Affect Out-of-Distribution Generalization and Calibration. IJCNN (2023)
Hiroki Naganuma, Kartik Ahuja, Shiro Takagi, Tetsuya Motokawa, Rio Yokota, Kohta Ishikawa, Ikuro Sato, Ioannis Mitliagkas
Empirical Study on Optimizer Selection for Out-of-Distribution Generalization. CoRR (2022)
Kilian Fatras, Hiroki Naganuma, Ioannis Mitliagkas
Optimal Transport meets Noisy Label Robust Loss and MixUp Regularization for Domain Adaptation. CoLLAs (2022)
Hiroki Naganuma, Hideaki Iiduka
Conjugate Gradient Method for Generative Adversarial Networks. CoRR (2022)
Kilian Fatras, Hiroki Naganuma, Ioannis Mitliagkas
Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation. CoRR (2022)
Hiroki Naganuma, Rio Yokota
A Performance Improvement Approach for Second-Order Optimization in Large Mini-batch Training. CCGRID (2019)
Kazuki Osawa, Akira Sekiya, Hiroki Naganuma, Rio Yokota
Accelerating Matrix Multiplication in Deep Learning by Using Low-Rank Approximation. HPCS (2017)