Skip to yearly menu bar Skip to main content


Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search

Youhei Akimoto · Shinichi Shirakawa · Nozomu Yoshinari · Kento Uchida · Shota Saito · Kouhei Nishida

Pacific Ballroom #53

Keywords: [ Optimization ] [ Architectures ] [ Algorithms ]


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 out-of-the-box to their own problems, albeit its purpose is to automate a part of tuning process. Aiming at a fast, robust, and widely-applicable NAS, we develop a generic optimization framework for NAS. We turn a coupled optimization of connection weights and neural architecture into a differentiable optimization by means of stochastic relaxation. It accepts arbitrary search space (widely-applicable) and enables to employ a gradient-based simultaneous optimization of weights and architecture (fast). We propose a stochastic natural gradient method with an adaptive step-size mechanism built upon our theoretical investigation (robust). Despite its simplicity and no problem-dependent parameter tuning, our method exhibited near state-of-the-art performances with low computational budgets both on image classification and inpainting tasks.

Live content is unavailable. Log in and register to view live content