Takafumi Kanamori (Ph.D.)
Title
Team Leader
Members
-
Team leaderTakafumi Kanamori
-
Postdoctoral researcherKosaku Takanashi
-
Visiting scientistTakashi Takenouchi
-
Visiting scientistWataru Kumagai
-
Visiting scientistHironori Fujisawa
-
Visiting scientistShotaro Akaho
-
Visiting scientistTakayuki Kawashima
-
Visiting scientistYuichiro Wada
-
Visiting scientistNoboru Murata
-
Junior research associateTakumi Nakagawa
Introduction
The research team aims to develop machine learning algorithms using non-convex optimization problems and its theoretical foundations. Most of current learning algorithms are formalized as convex optimization problems. Though the convexity is advantageous for optimization, it is not necessarily preferable from the standpoint of statistical properties such as robustness and bias-reduction of estimators. The optimization of non-convex functions, however, encounters computational difficulty. We challenge to develop learning algorithm using non-convex optimization beyond the scope of convexity and to establish a theoretical foundation to analyze learning methods with non-convexity.
Main Research Field
Computer Science
Research Field
Mathematics
Research Subjects
Theoretical analysis of learning algorithms using non-convex optimization
Statistical inference for large-scale models using divergence measures
Extension of multimodal information integration and information-transfer learning
Statistical inference for large-scale models using divergence measures
Extension of multimodal information integration and information-transfer learning
RIKEN Website URL
Introduction Video
Poster(s)
- FY2019 Research Results (Japanese version)
- FY2018 Research Results (Japanese version)
Related posts
posted on January 24, 2022 08:52Information
posted on March 29, 2021 07:40Seminar
posted on March 13, 2020 11:25Information
posted on September 11, 2019 12:00Information
posted on March 22, 2018 10:08Award
