Publications and Preprints

  1. Teshima, T.*, Ishikawa, I.*, Tojo, K., Oono, K., Ikeda, M., and Sugiyama, M.,
    Coupling-based invertible neural networks are universal diffeomorphism approximators. arXiv:2006.11469 [cs.LG].
    * Equal contribution.

    [preprint (arXiv)]
  2. Fujisawa, M., Teshima, T., and Sato, I.,
    γ-ABC: Outlier-robust approximate bayesian computation based on robust divergence estimator. arXiv:2006.07571 [stat.ML].
    [preprint (arXiv)]
  3. Kato, M. and Teshima, T.,
    Non-negative Bregman divergence minimization for deep direct density ratio estimation. arXiv:2006.06979 [cs.LG].
    [preprint (arXiv)]
  4. Teshima, T., Sato, I., and Sugiyama, M.,
    Few-shot domain adaptation by causal mechanism transfer. Thirty-seventh International Conference on Machine Learning, accepted (ICML 2020).
    [preprint (arXiv)] [video (10 min)] [slides] [code]
  5. Kato, M., Teshima, T., and Honda, J.,
    Learning from positive and unlabeled data with a selection bias. Seventh International Conference on Learning Representations, 2019 (ICLR 2019).
    [paper]
  6. Teshima, T., Xu, M., Sato, I., and Sugiyama, M.,
    Clipped matrix completion: a remedy for ceiling effects. Thirty-Third AAAI Conference on Artificial Intelligence, 2019 (AAAI-19).
    [paper] [supplementary] [code] [slides]