Efficient Architecture Search for Diverse Tasks

TL;DR

This paper introduces DASH, a fast differentiable NAS method that searches for optimal kernel sizes and dilations in CNNs, enabling efficient and effective AutoML across diverse tasks beyond computer vision.

Contribution

The paper proposes DASH, a novel differentiable NAS algorithm using Fourier diagonalization, achieving faster search times and broad applicability for diverse problem domains.

Findings

DASH outperforms state-of-the-art AutoML methods on multiple tasks.

DASH achieves near-training speed with high accuracy on several applications.

The approach generalizes well across domains like PDE solving and protein folding.

Abstract

While neural architecture search (NAS) has enabled automated machine learning (AutoML) for well-researched areas, its application to tasks beyond computer vision is still under-explored. As less-studied domains are precisely those where we expect AutoML to have the greatest impact, in this work we study NAS for efficiently solving diverse problems. Seeking an approach that is fast, simple, and broadly applicable, we fix a standard convolutional network (CNN) topology and propose to search for the right kernel sizes and dilations its operations should take on. This dramatically expands the model's capacity to extract features at multiple resolutions for different types of data while only requiring search over the operation space. To overcome the efficiency challenges of naive weight-sharing in this search space, we introduce DASH, a differentiable NAS algorithm that computes the mixture-of-operations using the Fourier diagonalization of convolution, achieving both a better asymptotic complexity and an up-to-10x search time speedup in practice. We evaluate DASH on ten tasks spanning a variety of application domains such as PDE solving, protein folding, and heart disease detection. DASH outperforms state-of-the-art AutoML methods in aggregate, attaining the best-known automated performance on seven tasks. Meanwhile, on six of the ten tasks, the combined search and retraining time is less than 2x slower than simply training a CNN backbone that is far less accurate.