Takeshi Teshima

Hi! I’m Takeshi Teshima, a 2nd-year Ph.D. student in Machine Learning at the Unversity of Tokyo (Graduate School of Frontier Sciences), advised by Professor Masashi Sugiyama. I am a member of the Sugiyama-Honda-Yokoya Laboratory, a Junior Research Associate at RIKEN AIP (national research center), and I am supported by Masason Foundation.

Previously I received B.Econ. from the University of Tokyo in 2017 and M.Sc. from the Unversity of Tokyo in 2019. In previous years, I have been honored to closely work with Professor Issei Sato as well as many other exceptional collaborators.

I am taking my first step toward AI for Good.

Research Interests 🔗

I’ve always been interested in generic methodology. I am currently working on developing statistical machine learning as one of the major frontiers of statistics/information technology.

  • Causality for machine learning.
    • Similarity of causal mechanisms as a foundation for transfer learning (causal mechanism transfer).
  • Machine learning for social sciences / natural sciences.
    • Recovering data from ceiling effects, a.k.a. censoring: clipped matrix completion.
  • Machine learning methodology in general.
    • Example: classification learning from limited information (positive-unlabeled classification), robust approximate Bayesian computation, density ratio estimation, and representation power of invertible neural networks.

CV 🔗

My CV can be found here.

Contacts 🔗

My email address can be found in the sidebar. If I’m not responsive for more than a few days, it is likely that your mail is wrongly classified as a spam. In such a case, please DM me on Twitter.

News and Upcoming Events 🔗

Jan 08 2021

We have been awarded IBIS 2020 Outstanding Presentation Award!

Nov 23 2020

Attending the 31st JASID Annual Conference (domestic conference on international development) to report our collaborative work at the PeaceTech working group with Ayaka Oishi from Peloria Insights. We are reporting our attempt to predict the destination of internally displaced persons (IDPs) using machine learning.

Nov 23 2020

Attending IBIS 2020 (online domestic conference)! Our talk will be in Session 3-4 (Nov 26th 15:30-17:30)!

11 Dec 2020

Happy to present our work "Universal Approximation Property of Neural Ordinary Differential Equations" at NeurIPS2020 Workshop: Differential Geometry meets Deep Learning (DiffGeo4DL)

07 Nov 2020

Successfully completed Omdena Save the Children project! Join one of Omdena´s upcoming projects: www.omdena.com/projects.

Older news are archived here.