3 citations · 8 across the 7 of their papers we have counts for
7 papers
Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime
Hiroki Naganuma, Taiji Suzuki, Rio Yokota +3
Generalization measures have been studied extensively in the machine learning community to better characterize generalization gaps. However, establishing a reliable generalization…
Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent
Hiroki Naganuma, Shagun Gupta, Youssef Briki +4
To maximize hardware utilization, modern machine learning systems typically employ large constant or manually tuned batch size schedules, relying on heuristics that are brittle and…
An Empirical Study of Pre-trained Model Selection for Out-of-Distribution Generalization and Calibration
Hiroki Naganuma, Ryuichiro Hataya, Kotaro Yoshida +1
In the field of computer vision, fine-tuning pre-trained models has become a prevalent strategy for out-of-distribution (OOD) generalization tasks. Different from most prior work t…
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths
Charles Guille-Escuret, Hiroki Naganuma, Kilian Fatras +1
Understanding the optimization dynamics of neural networks is necessary for closing the gap between theory and practice. Stochastic first-order optimization algorithms are known to…
Empirical Study on Optimizer Selection for Out-of-Distribution Generalization
Hiroki Naganuma, Kartik Ahuja, Shiro Takagi +5
Modern deep learning systems do not generalize well when the test data distribution is slightly different to the training data distribution. While much promising work has been acco…
Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
Kilian Fatras, Hiroki Naganuma, Ioannis Mitliagkas
It is common in computer vision to be confronted with domain shift: images which have the same class but different acquisition conditions. In domain adaptation (DA), one wants to c…
Conjugate Gradient Method for Generative Adversarial Networks
Hiroki Naganuma, Hideaki Iiduka
One of the training strategies of generative models is to minimize the Jensen--Shannon divergence between the model distribution and the data distribution. Since data distribution…