Kento Nozawa

12 October 2021


Kento Nozawa is a 4th year Ph.D. student who does research on machine learning. His current research interests are self-supervised representation learning and PAC-Bayes theory. He is supervised by Dr. Issei Sato at Issei Sato Lab in The University of Tokyo. He is also a part-time research assistant at RIKEN AIP. During summer 2019, he visited UCL AI Centre and Inria Lille Nord Europe Modal team to work on PAC-Bayes and contrastive representation learning. In order to live, he've been working for Optuna as a part-time machine learning engineer at Preferred Networks, Inc. since April 2021.

Hopefully, I’ll be graduating in Sept. 2022, so I’m on the job market.

Journal / Conference papers

  1. Kento Nozawa and Issei Sato. Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning. In NeurIPS, 2021. paper, slides, code, poster, arXiv.
  2. Kento Nozawa, Pascal Germain and Benjamin Guedj. PAC-Bayesian Contrastive Unsupervised Representation Learning. In UAI, pages 21–30, 2020. paper, video, slides, code, arXiv.
  3. Atsunori Kanemura, Yuhsen Cheng, Takumi Kaneko, Kento Nozawa and Shuichi Fukunaga. Imputing Missing Values in EEG with Multivariate Autoregressive Models. In EMBC, pages 2639–2642, 2018.


  1. Han Bao, Yoshihiro Nagano and Kento Nozawa. Sharp Learning Bounds for Contrastive Unsupervised Representation Learning. 2021. arXiv.Alphabetical ordering and equal contribution.
  2. Kento Nozawa and Issei Sato. PAC-Bayes Analysis of Sentence Representation. 2019. arXiv.