no code implementations • ICLR 2019 • Nozomu Yoshinari, Kento Uchida, Shota Saito, Shinichi Shirakawa, Youhei Akimoto
The experimental results show that the proposed architecture search method is fast and can achieve comparable performance to the existing methods.
1 code implementation • 19 Oct 2021 • Yoichi Hirose, Nozomu Yoshinari, Shinichi Shirakawa
Building the benchmark dataset for joint optimization of architecture and training hyperparameters is essential to further NAS research.
1 code implementation • 21 May 2019 • Youhei Akimoto, Shinichi Shirakawa, Nozomu Yoshinari, Kento Uchida, Shota Saito, Kouhei Nishida
It accepts arbitrary search space (widely-applicable) and enables to employ a gradient-based simultaneous optimization of weights and architecture (fast).