Hiroki Naganuma

According to our database, Hiroki Naganuma authored at least 10 papers between 2017 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of three.

2024

Towards Understanding Variants of Invariant Risk Minimization through the Lens of Calibration.

Kotaro Yoshida, Hiroki Naganuma

CoRR, 2024

2023

An Empirical Investigation of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration.

Hiroki Naganuma, Ryuichiro Hataya

CoRR, 2023

No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths.

Charles Guille-Escuret, Hiroki Naganuma, Kilian Fatras, Ioannis Mitliagkas

CoRR, 2023

Story-to-Images Translation: Leveraging Diffusion Models and Large Language Models for Sequence Image Generation.

Haruka Kumagai, Ryosuke Yamaki, Hiroki Naganuma

Proceedings of the 2nd Workshop on User-centric Narrative Summarization of Long Videos, 2023

How Image Corruption and Perturbation Affect Out-of-Distribution Generalization and Calibration.

Keigo Tada, Hiroki Naganuma

Proceedings of the International Joint Conference on Neural Networks, 2023

Conjugate Gradient Method for Generative Adversarial Networks.

Hiroki Naganuma, Hideaki Iiduka

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Empirical Study on Optimizer Selection for Out-of-Distribution Generalization.

Hiroki Naganuma, Kartik Ahuja, Shiro Takagi, Tetsuya Motokawa, Rio Yokota, Kohta Ishikawa, Ikuro Sato, Ioannis Mitliagkas

CoRR, 2022

Optimal Transport meets Noisy Label Robust Loss and MixUp Regularization for Domain Adaptation.

Kilian Fatras, Hiroki Naganuma, Ioannis Mitliagkas

Proceedings of the Conference on Lifelong Learning Agents, 2022

2019

A Performance Improvement Approach for Second-Order Optimization in Large Mini-batch Training.

Hiroki Naganuma, Rio Yokota

Proceedings of the 19th IEEE/ACM International Symposium on Cluster, 2019

2017

Accelerating Matrix Multiplication in Deep Learning by Using Low-Rank Approximation.

Kazuki Osawa, Akira Sekiya, Hiroki Naganuma, Rio Yokota

Proceedings of the 2017 International Conference on High Performance Computing & Simulation, 2017