Tam Le (RIKEN AIP)
 |
(a.k.a. Lê Thanh Tâm) |
Research interests: Optimal transport, tree-Wasserstein geometry, geometric machine learning, Riemannian manifold, topological data analysis, kernel methods, parametric optimization, metric learning.
Contact
RIKEN AIP (Kyoto University Office)
Artificial Intelligence Research Unit
Graduate School of Informatics, Kyoto University
Yoshida Honmachi, Sakyo-ku, Kyoto, 606-8501, Japan.
Email: tam.le[at]riken.jp or lttam.vn[at]gmail.com
My CV is here - Updated May, 2021.
News
08-May-2021, Our paper, entitled “Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search” has been accepted to ICML’21! This is joint work with Vu Nguyen, Makoto Yamada, and Michael A. Osborne.
23-Jan-2021, Two papers, entitled “Entropy Partial Transport with Tree Metrics: Theory and Practice” (joint work with Truyen Nguyen) — selected for oral presentation — and “Flow-based Alignment Approaches for Probability Measures in Different Spaces” (joint work with Nhat Ho and Makoto Yamada), have been accepted to AISTATS’21.
23-Jan-2021, Slides for my presentation (An Introduction on Tree-(Sliced)-Wasserstein Geometry) at RIKEN AIP Open Seminar Series, Virtual.
05-Apr-2020, Our proposal has been accepted by the Grants-in-Aid for Young Scientists as PI (04/2020 - 03/2023).
26-Oct-2019, Matlab code for tree-(sliced)-Wasserstein distance in our NeurIPS’19 (Tree-Sliced Variants of Wasserstein Distances) is available [Github].
04-Sep-2019, Our paper, entitled “Tree-Sliced Variants of Wasserstein Distances” has been accepted to NeurIPS’19! This is joint work with Marco Cuturi, Kenji Fukumizu, and Makoto Yamada.
11-Jul-2019, Slides for my presentation (Kernel methods for Persistence Diagrams: A Geometric Approach) at Institute for Advanced Study, Kyoto University.
25-Apr-2019, Python code for our ICML’19 (Safe Grid Search with Optimal Complexity) is available [Github], coded by Eugene Ndiaye.
22-Apr-2019, Our paper, entitled “Safe Grid Search with Optimal Complexity” has been accepted to ICML’19. This is joint work with Eugene Ndiaye, Olivier Fercoq, Joseph Salmon and Ichiro Takeuchi.
19-Oct-2018, Matlab code v0.1 for Persistence Fisher distance (Fisher information metric between two persistence diagrams with or without Fast Gauss Transform) is available [Github].
05-Sep-2018, Our paper, entitled “Persistence Fisher Kernel: A Riemannian Manifold Kernel for Persistence Diagrams” has been accepted to NeurIPS’18!
01-Sep-2017, Joined in High-Dimensional Statistical Modeling Team, RIKEN AIP as a postdoctoral researcher.
05-Apr-2017, Our proposal has been accepted by the Grants-in-Aid for Young Scientists (B) as PI (04/2017 - 03/2020).
Research Support
04/2020 - 03/2023, JSPS KAKENHI Grant number 20K19873, Grants-in-Aid for Young Scientists as PI (4.2M JPY).
04/2017 - 03/2020, JSPS KAKENHI Grant number 17K12745, Grants-in-Aid for Young Scientists (B) as PI (4.1M JPY).
Education
10/2012 - 09/2015, PhD program, Graduate school of Informatics, Kyoto University, Japan.
Supervisors: Professor Marco Cuturi, Professor Akihiro Yamamoto.
I completed my PhD program in September, 2015 and officially received my PhD degree in January, 2016.
Research Experience
09/2017 - present, Postdoctoral Researcher, High-Dimensional Statistical Modeling Team, RIKEN Center for Advanced Intelligence Project (RIKEN AIP).
Mentor: Professor Makoto Yamada
02/2016 - 08/2017, Postdoctoral Researcher, Nagoya Institute of Technology & National Institute for Materials Science, Japan.
Mentor: Professor Ichiro Takeuchi.
01/2016, Associate Researcher, Nagoya Institute of Technology, Japan.
Mentor: Professor Ichiro Takeuchi.
10/2015 - 12/2015, Associate Researcher, Kyoto University, Japan.
Mentors: Professor Akihiro Yamamoto, Professor Marco Cuturi.