On the Surrogate Gap between Contrastive and Supervised Losses
Han Bao*, Yoshihiro Nagano*, Kento Nozawa* (*: equal contribution)
ICML, 2022
proceeding / arxiv / presentation / code
Complex Energies of the Coherent Logitudinal Optical Phonon-plasmon Coupled Mode According to Dynamic Mode Decomposition Analysis
Itsushi Sakata, Takuya Sakata, Kohji Mizoguchi, Satoshi Tanaka, Goro Oohata, Ichiro Akai, Yasuhiko Igarashi, Yoshihiro Nagano, Masato Okada
Scientific Reports, 2021
Analysis of Trainability of Gradient-based Multi-environment Learning from Gradient Norm Regularization Perspective
Shiro Takagi, Yoshihiro Nagano, Yuki Yoshida, Masato Okada
International Joint Conference on Neural Networks (IJCNN), 2021
Statistical Mechanical Analysis of Catastrophic Forgetting in Continual Learning with Teacher and Student Networks
Haruka Asanuma, Shiro Takagi, Yoshihiro Nagano, Yuki Yoshida, Yasuhiko Igarashi, Masato Okada
Journal of the Physical Society of Japan, 2021
Collective dynamics of repeated inference in variational autoencoder rapidly find cluster structure
Yoshihiro Nagano, Ryo Karakida, Masato Okada
Scientific Reports, 2020
Normal mode analysis of a relaxation process with Bayesian inference
Itsushi Sakata, Yoshihiro Nagano, Yasuhiko Igarashi, Shin Murata, Kohji Mizoguchi, Ichiro Akai, and Masato Okada
Science and Technology of Advanced Materials, 2020
A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning
Yoshihiro Nagano, Shoichiro Yamaguchi, Yasuhiro Fujita, Masanori Koyama
International Conference on Machine Learning (ICML), 2019
proceeding / arxiv / code / slide
Input Response of Neural Network Model with Lognormally Distributed Synaptic Weights
Yoshihiro Nagano, Ryo Karakida, Norifumi Watanabe, Atsushi Aoyama, Masato Okada
Journal of the Physical Society of Japan, 2016
Analysis of Neural Circuit for Visual Attention Using Lognormally Distributed Input
Yoshihiro Nagano, Norifumi Watanabe, Atsushi Aoyama
Artificial Neural Networks and Machine Learning (ICANN), 2014