Keita Kume

Research Interests

• Signal processing, mechine learning, inverse problem
• Optimization (manifold optimization, nonsmooth optimization)

Lectures

• 2024: Basic Computer Programming (Tokyo Institute of Technology)
• 2019-2023(TA): Signal and System Analysis (Tokyo Institute of Technology)

Education

• March, 2024: Doctor's degree (Engineering), Tokyo Institute of Technology (supervisor: Prof. Isao Yamada)
• March, 2021: Master's degree (Engineering), Tokyo Institute of Technology (supervisor: Prof. Isao Yamada)
• March, 2019: Bachelor's degree (Engineering), Tokyo Institute of Technology (supervisor: Prof. Isao Yamada)

Work Experience

• October, 2024-Present: Assistant Professor, Dept. of Information and Communications Engineering, Institute of Science Tokyo
  (Institute of Science Tokyo opened on October 1, 2024, following the merger between Tokyo Institute of Technology and Tokyo Medical and Dental University)
• April, 2024-September, 2024: Assistant Professor, Dept. of Information and Communications Engineering, Tokyo Institute of Technology
• April, 2021-March, 2024: Research Fellow (DC1) of Japan Society for the Promotion of Science (JSPS)

Award

• December, 2024: IEEE SPS Japan Student Conference Paper Award
• March, 2021: Outstanding master's student award (Tokyo Institute of Technology, Dept. of Information and Communications Engineering)
• November, 2021: IEICE SIP Symposium, Young Researcher Encouragement Award

Preprint

1. S. Matsuo, K. Kume and I. Yamada, "Hierarchical Nash Equilibrium over Variational Equilibria via Fixed-point Set Expression of Quasi-nonexpansive Operator," arXiv:2409.11094. (arXiv)
2. K. Kume and I. Yamada, "Adaptive Localized Cayley Parametrization for Optimization over Stiefel Manifold," arXiv:2305.17901. (arXiv)

Journal Paper (peer-reviewd)

1. K. Kume and I. Yamada, "Adaptive Localized Cayley Parametrization for Optimization over Stiefel Manifold and Its Convergence Rate Analysis," IEEE Access, vol. 12, pp. 31312-31323, 2024. (official open access)
2. K. Kume and I. Yamada, "Generalized left-localized Cayley parametrization for optimization with orthogonality constraints," Optimization, vol. 73, no. 4, pp. 1113-1159, 2022. (official open access, arXiv)

International Conference (peer-reviewed)

1. K. Kume and I. Yamada, "A Variable Smoothing for Weakly Convex Composite Minimization with Nonconvex Constraint," arXiv:2412.04225 (to appear in IEEE ICASSP2025). (arXiv)
2. K. Kume and I. Yamada, "A Proximal Variable Smoothing for Nonsmooth Minimization Involving Weakly Convex Composite with MIMO Application," arXiv:2409.10934 (to appear in IEEE ICASSP2025). (arXiv)
3. S. Shoji, W. Yata, K. Kume and I. Yamada, "A Discrete-Valued Signal Estimation by Nonconvex Enhancement of SOAV with cLiGME Model," Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2024. (Oral presentation by Mr. Shoji) (official access, IEEE Xplore)
4. K. Kume and I. Yamada, "A variable smoothing for nonconvexly constrained nonsmooth optimization with application to sparse spectral clustering," 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 9296-9300, 2024 [IEEE SPS Japan Student Conference Paper Award]. (poster) (official access, arXiv, poster)
5. K. Kume and I. Yamada, "A global Cayley parametrization of Stiefel manifold for direct utilization of optimization mechanisms over vector spaces," 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5554-5558, 2021. (poster) (official access, poster)
6. K. Kume and I. Yamada, "A Nesterov-type acceleration with adaptive localized Cayley parametrization for optimization over the Stiefel manifold," 2020 28th European Signal Processing Conference (EUSIPCO), pp. 2105-2109, 2021. (poster) (official access)
7. K. Kume and I. Yamada, "Adaptive localized Cayley parametrization technique for smooth optimization over the Stiefel manifold" 2019 27th European Signal Processing Conference (EUSIPCO), pp. 1-5, 2021. (poster) (official access)

Invited talk

1. 久米啓太, "弱凸関数と可微分写像からなる合成関数の最適化のための可変平滑化法と信号処理応用," 最適化の理論とアルゴリズム（RAOTA）第8回研究会. (RAOTA, Presentation slide in Japanese)
2. K. Kume and I. Yamada, "Cayley parametrization strategy for optimization over the Stiefel manifold," 10th International Congress on Industrial and Applied Mathematics (ICIAM 2023), 2023.
3. K. Kume and I. Yamada, "On optimization over Stiefel manifold based on adaptive Cayley parametrization," IEICE Technical Report, vol. 123, no. 152, SIP2023-50, pp. 20-20, 2023.