Okuno Takayuki

オクノタカユキ | Okuno Takayuki

Affiliation and department：
Job title： Associate Professor
Homepage URL (1)： https://sites.google.com/view/takaoku-web-page/english-page?authuser=0

Research field (1)： Mathematical informatics

Research keywords (5)： Semi-infinite Optimization , Concic Optimization , Mathematical Programming , Continuous optimization , Optimization

Research theme for competitive and other funds (4)：

2025 - 2030 Development of large-scale bilevel optimization algorithms and their applications to machine learning
2020 - 2025 Development of nonlinear semidefinite optimization theory and application to machine learning
2020 - 2024 Theory and algorithms for ill-conditioned conic linear programming
2015 - 2019 Development of fast algorithms for semi-infinite programs with conic constraints and application to practical problems

Papers (28)：

Takuma TAKAHATA, Norito MINAMIKAWA, Takayuki OKUNO. Computational Complexity and Integer Programming Formulation of the Oredango Puzzle. IEICE Transactions on Information and Systems. 2025
Takayuki Okuno. Analysis of the primal-dual central path for nonlinear semidefinite optimization without the nondegeneracy condition. Mathematics of Operations Research. 2025
Mitsuaki Obara, Takayuki Okuno, Akiko Takeda. Local near-quadratic convergence of Riemannian interior point methods. to appear in Journal of Optimzation Theory and Applications. 2025
Naoki Marumo, Takayuki Okuno, Akiko Takeda. Accelerated-gradient-based generalized Levenberg-Marquardt method with oracle complexity bound and local quadratic convergence. Mathematical Programming. 2024
Takashi Tsuchiya, Bruno F. Lourenço, Masakazu Muramatsu, Takayuki Okuno. Closing duality gaps of SDPs completely through perturbation when singularity degree is one. Optimization Methods and Software. 2024. 39. 5. 1040-1067

ｍore...

MISC (4)：

Mitsuaki Obara, Takayuki Okuno, Akiko Takeda. A primal-dual interior point trust region method for second-order stationary points of Riemannian inequality-constrained optimization problems. 2025
Adachi, Sho, Okuno, Takayuki, Takeda, Akiko. Riemannian Levenberg-Marquardt Method with Global and Local Convergence Properties. arXiv preprint arXiv:2210.00253. 2022
M. Muramatsu, T. Kitahara, B. F. Loureco, T. Okuno, T. Tsuchiya. An oracle-based projection and rescaling algorithm for linear semi-infinite feasibility problems and its application to SDP and SOCP. arXiv preprint arXiv:1809.10340. 2018
Okuno Takayuki, Hayashi Shunsuke, Fukushima Masao. Optimality Conditions and Algorithms for Semi-Infinite Programs with an Infinite Number of Second-Order Cone Constraints (The evolution of optimization models and algorithms). RIMS Kokyuroku. 2011. 1726. 161-171

Books (2)：

Lectures and oral presentations (14)：

A bilevel approach to l q hyperpa- rameter optimization
(nternational Conference on Nonlinear Analysis and Convex Analysis International Conference on Optimization Techniques and Applications 2019)
Smoothing Newton method for l q hyperparameter optimization
(The PolyU AMA - RIKEN AIP Joint Workshop on Optimization and Machine Learning 2019)
Hyperparameter learning for sparse l p regularizers via nonsmooth bilevel op- timization
(019 Optimization Workshop Department of Mathematics 2019)
微分不可能な2段階最適化を用いたハイパーパラメータ学習について
(第21回情報論的学習理論ワークショップ 2018)
微分不可能な2段階最適化を用いたハイパーパラメータ選択について
(日本オペレーションズ・リサーチ学会2018年秋季研究発表 2018)

ｍore...

Education (1)：

Professional career (1)：

Work history (3)：

2022/04 - 現在 Seikei University Faculty of Science and Technology Department of Science and Technology Associate Professor
2017/07 - 2022/03 理化学研究所革新知能統合研究センター研究員
2013/04 - 2017/06 Tokyo University of Science Management Science, Faculty of Engineering

Awards (2)：

Association Membership(s) (2)：

日本オペレーションズリサーチ学会 , 日本応用数理学会

※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page