Alert button
Picture for Hiroki Naganuma

Hiroki Naganuma

Alert button

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

Jan 31, 2024
Kotaro Yoshida, Hiroki Naganuma

Viaarxiv icon

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

Jul 17, 2023
Hiroki Naganuma, Ryuichiro Hataya

Viaarxiv icon

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

Jun 20, 2023
Charles Guille-Escuret, Hiroki Naganuma, Kilian Fatras, Ioannis Mitliagkas

Figure 1 for No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths
Figure 2 for No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths
Figure 3 for No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths
Figure 4 for No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths
Viaarxiv icon

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

Nov 18, 2022
Hiroki Naganuma, Kartik Ahuja, Shiro Takagi, Tetsuya Motokawa, Rio Yokota, Kohta Ishikawa, Ikuro Sato, Ioannis Mitliagkas

Figure 1 for Empirical Study on Optimizer Selection for Out-of-Distribution Generalization
Figure 2 for Empirical Study on Optimizer Selection for Out-of-Distribution Generalization
Figure 3 for Empirical Study on Optimizer Selection for Out-of-Distribution Generalization
Figure 4 for Empirical Study on Optimizer Selection for Out-of-Distribution Generalization
Viaarxiv icon

Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation

Jun 22, 2022
Kilian Fatras, Hiroki Naganuma, Ioannis Mitliagkas

Figure 1 for Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
Figure 2 for Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
Figure 3 for Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
Figure 4 for Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
Viaarxiv icon

Conjugate Gradient Method for Generative Adversarial Networks

Mar 28, 2022
Hiroki Naganuma, Hideaki Iiduka

Figure 1 for Conjugate Gradient Method for Generative Adversarial Networks
Figure 2 for Conjugate Gradient Method for Generative Adversarial Networks
Figure 3 for Conjugate Gradient Method for Generative Adversarial Networks
Figure 4 for Conjugate Gradient Method for Generative Adversarial Networks
Viaarxiv icon