Publications

Unsupervised Learning of Equivariant Structure from Sequence

NeurIPS 2022

Machine Learning / Deep Learning

By : Takeru Miyato, Masanori Koyama, Kenji Fukumizu

Reconnaissance for Reinforcement Learning with Safety Constraints

ECML2021

Reinforcement Learning

By : Shin-ichi Maeda, Hayato Watahiki, Yi Ouyang, Shintarou Okada, Masanori Koyama, Prabhat Nagarajan

Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN

IJCV 2020

Computer Vision

Machine Learning / Deep Learning

By : Masaki Saito, Shunta Saito, Masanori Koyama, Sosuke Kobayashi

Learning Structured Latent Factors from Dependent Data:A Generative Model Framework from Information-Theoretic Perspective

ICML 2020

Machine Learning / Deep Learning

By : Ruixiang Zhang, Masanori Koyama, Katsuhiko Ishiguro

A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation

NeurIPS 2019

Machine Learning / Deep Learning

By : Mitsuru Kusumoto, Takuya Inoue, Gentaro Watanabe, Takuya Akiba, Masanori Koyama

Robustness to Adversarial Perturbations in Learning from Incomplete Data

NeurIPS 2019

Machine Learning / Deep Learning

By : Amir Najafi, Shin-ichi Maeda, Masanori Koyama, Takeru Miyato

A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning

ICML2019

By : Yoshihiro Nagano, Shoichiro Yamaguchi, Yasuhiro Fujita, Masanori Koyama

Distributional Concavity Regularization for GANs

ICLR 2019

Machine Learning / Deep Learning

By : Shoichiro Yamaguchi, Masanori Koyama

Spectral Normalization for Generative Adversarial Networks

ICLR 2018

Machine Learning / Deep Learning

By : Takeru Miyato, Toshiki Kataoka, Masanori Koyama, Yuichi Yoshida

cGANs with Projection Discriminator

ICLR 2018

Machine Learning / Deep Learning

By : Takeru Miyato, Masanori Koyama

Synthetic Gradient Methods with Virtual Forward-Backward Networks

ICLR2017 Workshop

Machine Learning / Deep Learning

By : Takeru Miyato, Daisuke Okanohara, Shin-ichi Maeda, Masanori Koyama

Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning

IEEE TPAMI

Machine Learning / Deep Learning

By : Takeru Miyato, Shin-ichi Maeda, Masanori Koyama, Shin Ishii