Ryotaro Mitsuboshi's Home Page
(EN/JP)
Check my résumé.
Ph.D. Thesis: Frank-Wolfe-based Boosting Algorithms and Its Extensions
I am Ryotaro Mitsuboshi, and I have a Ph. D. in Information Science.
I'm highly interested in machine learning algorithms
and their theories,
especially for boosting algorithms.
I'm continuing my research as a hobby
while I work as a programmer.
I'm looking for a job
where I can study the theoretical side of machine learning.
Research interests
- Machine Learning
- Boosting
- Support Vector Machines
- Statistical Learning Theory
- Online Learning
- Convex optimization
Publications
-
Ryotaro Mitsuboshi, Kohei Hatano, and Eiji Takimoto.
Online Combinatorial Linear Optimization via a Frank-Wolfe-based Metarounding Algorithm.
IEICE Transactions on Information and Systems 2024
[paper]
[arXiv]
[code]
-
Yuta Kurokawa, Ryotaro Mitsuboshi, Haruki Hamasaki, Kohei Hatano, Eiji Takimoto, and Holakou Rahmanian.
Extended Formulations via Decision Diagrams.
COCOON 2023
[paper]
[arXiv]
[code]
[slide]
-
Ryotaro Mitsuboshi, Kohei Hatano, and Eiji Takimoto.
Solving Linear Regression with Insensitive Loss by Boosting.
IEICE Transactions on Information and Systems 2024
[paper]
[code]
-
Ryotaro Mitsuboshi, Kohei Hatano, and Eiji Takimoto.
Boosting as Frank-Wolfe.
Preprint
[arXiv]
[code]
Workshops
Projects
-
MiniBoosts.
A collection of boosting algorithms written in Rust.
-
Bandit.
A small collection of bandit algorithms written in Rust.
Last updated: 2024/10/16
Contact: rmitsuboshi.research[at]gmail.com
