Details
Presenter(s)
Display Name
Liewen Liao
- Affiliation
-
AffiliationShanghai Jiao Tong University
- Country
Abstract
Differentiable architecture search (DARTS) has achieved success in searching powerful network architectures but suffers from unstable search,high search cost from repetitive attempts and unawareness of computational cost. In this paper, we propose a novel approach, namely Efficient and Stable Differentiable Architecture Search (ES-DARTS), that leverages decoupled search strategy and variational proxy pruning to achieve efficient search for efficient neural networks.