Takashi Ishida

alt text 

Takashi Ishida

Lecturer,
Department of Complexity Science and Engineering,
Graduate School of Frontier Sciences,
The University of Tokyo.

Email: ishi at k.u-tokyo dot ac dot jp
URL: https://takashiishida.github.io

Biography

I am a Lecturer at Department of Complexity Science and Engineering, Graduate School of Frontier Sciences, The University of Tokyo. I am also affiliated with Department of Computer Science, Graduate School of Information Science and Technology and Department of Information Science, Faculty of Science.

I received my PhD from the University of Tokyo in 2021, advised by Prof. Masashi Sugiyama. Prior to that, I received the MSc from the University of Tokyo in September 2017 and the Bachelor of Economics from Keio University in March 2013.

Research Interests

Publications

Conference Papers (Full Review)

  1. T. Ishida, I. Yamane, T. Sakai, G. Niu, M. Sugiyama.
    Do We Need Zero Training Loss After Achieving Zero Training Error?
    In Proceedings of Thirty-seventh International Conference on Machine Learning (ICML2020).
    [paper] [code]

  2. T. Ishida, G. Niu, A. K. Menon, and M. Sugiyama.
    Complementary-label learning for arbitrary losses and models.
    In Proceedings of Thirty-sixth International Conference on Machine Learning (ICML2019).
    [paper] [poster] [slides] [video] [code]

  3. T. Ishida, G. Niu, and M. Sugiyama.
    Binary classification from positive-confidence data.
    In Advances in Neural Information Processing Systems 31 (NeurIPS2018).
    Note: This paper was selected for spotlight presentation.
    [paper] [poster] [slides] [video] [code]

  4. T. Ishida, G. Niu, W. Hu, and M. Sugiyama.
    Learning from complementary labels.
    In Advances in Neural Information Processing Systems 30 (NeurIPS2017).
    [paper]

Journal Papers (Full Review)

  1. Z. Lu, C. Xu, B. Du, T. Ishida, L. Zhang, & M. Sugiyama.
    LocalDrop: A hybrid regularization for deep neural networks.
    IEEE Transactions on Pattern Analysis and Machine Intelligence, to appear.

  2. T. Ishida.
    Forecasting Nikkei 225 Returns By Using Internet Search Frequency Data.
    In Securities Analysts Journal, vol.52, no.6, pp.83-93 (selected as Research Notes), 2014.

Experiences

Grants and Fellowships

Awards

Program Committee/Reviewer

Conferences

Journals

Other