# RADARS: Memory Efficient Reinforcement Learning Aided Differentiable Neural Architecture Search

Source: [RADARS: Memory Efficient Reinforcement Learning Aided Differentiable Neural Architecture Search](<https://www.sota2.com/research/paper/68fa6ab51e209131cea29e95>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:09:35.928Z

Authors: Zheyu Yan, Weiwen Jiang, Xiaobo Sharon Hu, Yiyu Shi

Published: 2021-09-13T04:00:33.000Z

## Abstract

Differentiable neural architecture search (DNAS) is known for its capacity in the automatic generation of superior neural networks. However, DNAS based methods suffer from memory usage explosion when the search space expands, which may prevent them from running successfully on even advanced GPU platforms. On the other hand, reinforcement learning (RL) based methods, while being memory efficient, are extremely time-consuming. Combining the advantages of both types of methods, this paper presents RADARS, a scalable RL-aided DNAS framework that can explore large search spaces in a fast and memory-efficient manner. RADARS iteratively applies RL to prune undesired architecture candidates and identifies a promising subspace to carry out DNAS. Experiments using a workstation with 12 GB GPU memory show that on CIFAR-10 and ImageNet datasets, RADARS can achieve up to 3.41% higher accuracy with 2.5X search time reduction compared with a state-of-the-art RL-based method, while the two DNAS baselines cannot complete due to excessive memory usage or search time. To the best of the authors' knowledge, this is the first DNAS framework that can handle large search spaces with bounded memory usage.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2109.05691>)

[PDF](<https://arxiv.org/pdf/2109.05691.pdf>)
