Half Search Space is All You Need

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rumiantsev, Pavel, Coates, Mark
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910955179343872
author Rumiantsev, Pavel
Coates, Mark
author_facet Rumiantsev, Pavel
Coates, Mark
contents Neural Architecture Search (NAS) is a powerful tool for automating architecture design. One-Shot NAS techniques, such as DARTS, have gained substantial popularity due to their combination of search efficiency with simplicity of implementation. By design, One-Shot methods have high GPU memory requirements during the search. To mitigate this issue, we propose to prune the search space in an efficient automatic manner to reduce memory consumption and search time while preserving the search accuracy. Specifically, we utilise Zero-Shot NAS to efficiently remove low-performing architectures from the search space before applying One-Shot NAS to the pruned search space. Experimental results on the DARTS search space show that our approach reduces memory consumption by 81% compared to the baseline One-Shot setup while achieving the same level of accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13586
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Half Search Space is All You Need
Rumiantsev, Pavel
Coates, Mark
Machine Learning
Neural Architecture Search (NAS) is a powerful tool for automating architecture design. One-Shot NAS techniques, such as DARTS, have gained substantial popularity due to their combination of search efficiency with simplicity of implementation. By design, One-Shot methods have high GPU memory requirements during the search. To mitigate this issue, we propose to prune the search space in an efficient automatic manner to reduce memory consumption and search time while preserving the search accuracy. Specifically, we utilise Zero-Shot NAS to efficiently remove low-performing architectures from the search space before applying One-Shot NAS to the pruned search space. Experimental results on the DARTS search space show that our approach reduces memory consumption by 81% compared to the baseline One-Shot setup while achieving the same level of accuracy.
title Half Search Space is All You Need
topic Machine Learning
url https://arxiv.org/abs/2505.13586