50 citations · 68 across the 4 of their papers we have counts for
5 papers
NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameters
Yoichi Hirose, Nozomu Yoshinari, Shinichi Shirakawa
The benchmark datasets for neural architecture search (NAS) have been developed to alleviate the computationally expensive evaluation process and ensure a fair comparison. Recent N…
Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search
Youhei Akimoto, Shinichi Shirakawa, Nozomu Yoshinari +3
High sensitivity of neural architecture search (NAS) methods against their input such as step-size (i.e., learning rate) and search space prevents practitioners from applying them…
Parameterless Stochastic Natural Gradient Method for Discrete Optimization and its Application to Hyper-Parameter Optimization for Neural Network
Kouhei Nishida, Hernan Aguirre, Shota Saito +2
Black box discrete optimization (BBDO) appears in wide range of engineering tasks. Evolutionary or other BBDO approaches have been applied, aiming at automating necessary tuning of…
Sample Reuse via Importance Sampling in Information Geometric Optimization
Shinichi Shirakawa, Youhei Akimoto, Kazuki Ouchi +1
In this paper we propose a technique to reduce the number of function evaluations, which is often the bottleneck of the black-box optimization, in the information geometric optimiz…
Dynamic Optimization of Neural Network Structures Using Probabilistic Modeling
Shinichi Shirakawa, Yasushi Iwata, Youhei Akimoto
Deep neural networks (DNNs) are powerful machine learning models and have succeeded in various artificial intelligence tasks. Although various architectures and modules for the DNN…