Yusuke Tsuzuku

Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks

Yusuke Tsuzuku, Issei Sato, Masashi Sugiyama · arXiv (Cornell University) · 2018 · 108 citations · Full text

Neural Scaling Law, Deep Neural Networks, Engineering +15

Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networks

Yusuke Tsuzuku, Issei Sato, Masashi Sugiyama · arXiv (Cornell University) · 2018 · 76 citations · Full text

Neural Scaling Law, Deep Neural Networks, Engineering +15

On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions

Yusuke Tsuzuku, Issei Sato · 2019 · 54 citations

Geometric Learning, Convolutional Neural Network, Engineering +19

Variance-based Gradient Compression for Efficient Distributed Deep Learning

Yusuke Tsuzuku, Hiroto Imachi, Takuya Akiba · arXiv (Cornell University) · 2018 · 50 citations · Full text

Convolutional Neural Network, Distributed Deep Learning, Engineering +14

Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks using PAC-Bayesian Analysis

Yusuke Tsuzuku, Issei Sato, Masashi Sugiyama · arXiv (Cornell University) · 2019 · 14 citations · Full text

Engineering, Machine Learning, Normalized Flat Minima +17