Centers & Labs

RIKEN Center for Advanced Intelligence Project

Imperfect Information Learning Team

Team Leader: Masashi Sugiyama (D.Eng.)
Masashi  Sugiyama(D.Eng.)

Recently, machine learning technology with big data has been actively investigated and its effectiveness has been demonstrated. However, depending on application domains, it is difficult or even it is not possible to collect a large amount of data. In the Imperfect Information Learning Team, for various machine learning tasks including supervised learning, unsupervised learning, and reinforcement learning, we develop novel algorithms that allow accurate learning from limited information. We also elucidate their theoretical properties and apply them to various real-world applications ranging from fundamental science to business.

Main Research Field

Computer Science

Related Research Fields

Engineering / Mathematics

Research Subjects

  • Development of machine learning algorithms from imperfect information
  • Theoretical analysis of machine learning algorithms
  • Real-world application of machine learning algorithms

Selected Publications

  1. Sasaki, H., Kanamori, T., Hyvärinen, A., Niu, G., & Sugiyama, M.
    “Mode-seeking clustering and density ridge estimation via direct estimation of density-derivative-ratios.”
    arXiv:1707.01711, (2017).
  2. Ishida, T., Niu, G., & Sugiyama, M.
    “Learning from complementary labels.”
    arXiv:1705.07541, (2017).
  3. Kiryo, R., Niu, G., du Plessis, M. C., & Sugiyama, M.
    “Positive-unlabeled learning with non-negative risk estimator.”
    arXiv:1703.00593, (2017).
  4. Sakai, T., du Plessis, M. C., Niu, G., & Sugiyama, M.
    “Semi-supervised classification based on classification from positive and unlabeled data.”
    Proceedings of 34th International Conference on Machine Learning (ICML2017), Sydney, Australia, Aug. 6-12, (2017), to appear.
  5. Hu, W., Miyato, T., Tokui, S., Matsumoto, E., & Sugiyama, M.
    “Learning discrete representations via information maximizing self-augmented training.”
    Proceedings of 34th International Conference on Machine Learning (ICML2017), Sydney, Australia, Aug. 6-12, (2017), to appear.
  6. Tangkaratt, V., Sasaki, H., & Sugiyama, M.
    “Direct estimation of the derivative of quadratic mutual information with application in supervised dimension reduction.”
    Neural Computation, to appear
  7. Sasaki, H., Kanamori, T., & Sugiyama, M.
    “Estimating density ridges by direct estimation of density-derivative-ratios. “
    In Proceedings of 29th International Conference on Artificial Intelligence and Statistics (AISTATS2017), vol.54, pp.204-212, Fort Lauderdale, Florida, USA, Apr. 20-22, (2017).
  8. Ashizawa, M., Sasaki, H., Sakai, T., & Sugiyama, M.
    “Least-squares log-density gradient clustering for Riemannian manifolds.”
    In Proceedings of 29th International Conference on Artificial Intelligence and Statistics (AISTATS2017), Proceedings of Machine Learning Research, vol.54, pp.537-546, Fort Lauderdale, Florida, USA, Apr. 20-22, (2017).
  9. Tangkaratt, V., van Hoof, H., Parisi, S., Neumann, G., Peters, J., & Sugiyama, M.
    “Policy search with high-dimensional context variables.”
    In Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI2017), pp.2632-2638, San Francisco, California, USA, Feb. 4-9, (2017).
  10. Niu, G., du Plessis, M. C., Sakai, T., Ma, Y., & Sugiyama, M.
    “Theoretical comparisons of positive-unlabeled learning against positive-negative learning.”
    In Advances in Neural Information Processing Systems 29 (NIPS2016), pp.1199-1207, Barcelona, Spain, Dec. 5-8, (2016).

Contact information

Nihonbashi 1-chome Mitsui Building, 15th floor,
1-4-1 Nihonbashi,
Chuo-ku, Tokyo
103-0027, Japan

Email: masashi.sugiyama [at] riken.jp

Related links