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’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.
My CV can be found here.
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
|22 Oct 2020|
Excited to host a talk event: Transfer Learning between Largely Different Distributions.
|21 Oct 2020|
Honored to be recognized as a top 10% reviewer for NeurIPS 2020!
|26 Aug 2020|
Our paper "Coupling-based invertible neural networks are universal diffeomorphism approximators" has been accepted at NeurIPS 2020 for oral presentation! (105 orals among the 1900 accepted papers; paper acceptance rate 20.1%).
|20 Aug 2020|
Thrilled to take part in the Omdena SaveTheChildren project (8 weeks).
|6 Sep 2020|
Giving a talk at Math-iine Learning study group.
Older news are archived here.