Neural Architecture Search as Sparse Supernet
This work addresses the challenge of efficiently automating neural architecture design for machine learning practitioners, though it appears incremental by building on existing NAS methods.
The paper tackles the problem of Neural Architecture Search (NAS) by extending it to automated Mixed-Path Search, modeling it as a sparse supernet with a new continuous representation and sparsity constraints, resulting in the ability to search for compact, general, and powerful neural architectures as demonstrated in experiments on Convolutional and Recurrent Neural Networks.
This paper aims at enlarging the problem of Neural Architecture Search (NAS) from Single-Path and Multi-Path Search to automated Mixed-Path Search. In particular, we model the NAS problem as a sparse supernet using a new continuous architecture representation with a mixture of sparsity constraints. The sparse supernet enables us to automatically achieve sparsely-mixed paths upon a compact set of nodes. To optimize the proposed sparse supernet, we exploit a hierarchical accelerated proximal gradient algorithm within a bi-level optimization framework. Extensive experiments on Convolutional Neural Network and Recurrent Neural Network search demonstrate that the proposed method is capable of searching for compact, general and powerful neural architectures.