Shirakawa Laboratory

Our paper has been published in IEEE ACCESS. This paper proposes a surrogate benchmark for practical scenarios in the joint optimization of neural architecture and hyperparameters.

Yoichi Hirose, Kento Uchida, and Shinichi Shirakawa: NAS-HPO-Bench-II-Plus: A Surrogate Benchmark Dataset toward Practical Scenarios in Joint Neural Architecture Search and Hyperparameter Optimization, IEEE Access, Vol. 14, pp. 108050-108062, Jul. 2026. [DOI]

The collaborative paper with Prof. Akimoto’s group has been accepted to the 19th International Conference on Parallel Problem Solving From Nature (PPSN 2026). This paper proposes a bilevel optimization framework for mixed categorical-continuous black-box optimization.

• Marc Ong, Shinichi Shirakawa, Youhei Akimoto, Mixed-Categorical Black-Box Optimization via Information-Geometric Bilevel Decomposition, 19th International Conference on Parallel Problem Solving From Nature (PPSN 2026),Trento, Italy, August 29 - September 2, 2026. (Accepted) [arXiv]

Our paper has been accepted to the 28th International Conference on Pattern Recognition (ICPR 2026). This paper proposes a model-merging-based continual learning method that can consider performance preferences.

• Kei Hiroshima, Kento Uchida, Shinichi Shirakawa: Tunable MAGMAX: Preference-Aware Model Merging for Continual Learning, 28th International Conference on Pattern Recognition (ICPR 2026), Lyon, France, August 17-22, 2026.

Our papers (four full papers) have been accepted to the Genetic and Evolutionary Computation Conference (GECCO 2026) (San José, Costa Rica (hybrid), July 13-17, 2026).

• Haruhito Nakagawa, Kento Uchida, and Shinichi Shirakawa: Evaluation of Element-wise Effectiveness Estimation for Augmented Lagrangian CMA-ES (Accepted as a Full Paper)
• Sota Hamada, Yutaro Yamada, Kento Uchida, and Shinichi Shirakawa: Hierarchical Evolution Strategy for Optimization of Sharp Ridge (Accepted as a Full Paper)
• Kento Uchida, Ryoki Hamano, Masahiro Nomura, and Shinichi Shirakawa: Adaptive Stochastic Natural Gradient Method for Safe Optimization on Binary Space (Accepted as a Full Paper)
• Ryoki Hamano, Kento Uchida, and Shinichi Shirakawa: Convergence Analysis of Evolution Strategies for Mixed-Integer Optimization (Accepted as a Full Paper)

Yutaro Yamada (Doctoral Student) was selected as an Outstanding Student at Evostar 2026. Congratulations!

Our paper has been accepted and presented at EvoCOP 2026 (Part of EvoStar 2026). This paper proposes a weight adaptation method for adaptive stochastic natural gradient in black-box binary optimization.

• Yutaro Yamada, Kento Uchida, Shinichi Shirakawa: Weight Adaptation for Improving Parallel Performance of Adaptive Stochastic Natural Gradient, 26th European Conference on Evolutionary Computation in Combinatorial Optimization (EvoCOP 2026, Part of EvoStar 2026), Toulouse, France, April 8-10, 2026. (Best Paper Nomination) [DOI]

Members’ Page has been updated. Now, our laboratory has 2 faculty members, 1 secretary, 1 postdoctoral researcher, 14 master’s course students, and 6 undergraduate students for graduation research.

Our papers (one regular paper and one short paper) have been accepted to the Pacific Rim International Conference on Artificial Intelligence (PRICAI 2025) (Wellington, New Zealand, November 17-21, 2025).

• Keisuke Sugawara, Kento Uchida, and Shinichi Shirakawa: Neural Architecture Search of Sample Reweighting Networks for Complex Distribution Shift (Accepted as a Regular Paper)
• Daiki Yotsufuji, Kenta Nishihara, Shoma Shimizu, Kento Uchida, and Shinichi Shirakawa: OnDeFog: Online Decision Transformer under Frame Dropping (Accepted as a Short Paper)

Our paper has been accepted to the 51st Annual Conference of the IEEE Industrial Electronics Society (IECON 2025). This paper proposes uncertainty-aware self-localization for bulldozers based on machine learning. This work is a collaborative research with Komatsu Ltd.

• Hikaru Sawafuji, Ryota Ozaki, Takuto Motomura, Toyohisa Matsuda, Masanori Tojima, Kento Uchida, and Shinichi Shirakawa: Uncertainty-Aware Self-Localization for Bulldozers Using Machine Learning with Internal Sensor Data, The 51st Annual Conference of the IEEE Industrial Electronics Society (IECON 2025), Madrid, Spain, October 14-17, 2025. (Accepted)

We presented on surrogate benchmarks for model merging optimization at AutoML 2025 Non-Archival Content Track.

• Rio Akizuki, Yuya Kudo, Nozomu Yoshinari, Yoichi Hirose, Toshiyuki Nishimoto, Kento Uchida, and Shinichi Shirakawa: Surrogate Benchmarks for Model Merging Optimization, International Conference on Automated Machine Learning (AutoML 2025), Non-Archival Content Track, New York City, USA, September 8-11, 2025. [Link] [arXiv]