Research
I am an Assistant Professor in Graduate School of Information Science and Technology at The University of Tokyo, working in Mathematical Informatics 5th Lab led by Prof. Akiko Takeda. I received my M.Sc. from Tokyo Institute of Technology in 2020 (supervisor: Prof. Mituhiro Fukuda), and my Ph.D. from SOKENDAI in 2023 (supervisor: Prof. Mirai Tanaka).
My research interests include optimization and its algorithms. I am also interested in its applications.
Research Area:
- Optimization: Nonconvex Optimization, Convex Optimization, First-Order Methods, Bregman Divergence, Projection-Free Methods
- Applications: Machine Learning, Signal Processing
Contact
Faculty of Engineering Bldg.14-529, Hongo Campus, The University of Tokyo
News
- Our papers on accelerated Bregman proximal gradient, Newton Frank–Wolfe, and nonlinearly preconditioned GD are now available on arXiv.
- My paper "Adaptive Conditional Gradient Sliding: Projection-Free and Line-Search-Free Acceleration" is accepted at NeurIPS 2026.
- I gave a talk at 2026 SIAM Conference on Optimization.
- I gave a poster presentation about "Fast Frank–Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions" at ICLR 2026.
- My paper "Adaptive Conditional Gradient Sliding: Projection-Free and Line-Search-Free Acceleration" is now available on arXiv.
- Our paper "Fast Frank–Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions" is accepted at ICLR 2026.
- Our paper "Approximate Bregman proximal gradient algorithm with variable metric Armijo–Wolfe line search" is now available on arXiv.
- Our paper "Majorization-minimization Bregman proximal gradient algorithms for NMF with the Kullback–Leibler divergence" is accepted at Journal of Optimization Theory and Applications.
- I gave a talk at ICCOPT 2025.
- Our paper "Fast Frank–Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions" is now available on arXiv.
- Our paper "Approximate Bregman proximal gradient algorithm for relatively smooth nonconvex optimization" is accepted at Computational Optimization and Applications.
- I'll give a talk at ISMP 2024.
- Our paper "Majorization-minimization Bregman proximal gradient algorithms for nonnegative matrix factorization with the Kullback--Leibler divergence" is now available on arXiv.
- Our paper "Approximate Bregman proximal gradient algorithm for relatively smooth nonconvex optimization" is now available on arXiv.
- I start as an Assistant Professor at The Univeristy of Tokyo
