Skip to content
Back to skills

Zerocost Proxies For Lightweight Nas

ASecurity

**arXiv ID:** 2101.08134 **Authors:** Mohamed S. Abdelfattah, Abhinav Mehrotra, Łukasz Dudziak, Nicholas D. Lane **Published:** 2021-01-20T13:59:52Z **Abstract:** Neural Architecture Search (NAS) is quickly becoming the standard methodology to design neural network models. However, NAS is typically compute-intensive because multiple models need to be evaluated before choosing the best one. To reduce the computational power and time needed, a proxy task is often used for evaluating each model ...

  • 3 stars
  • 0 votes
  • 0 copies
  • 5 views
  • Added September 11, 2026
toolsgogit

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill zerocost-proxies-for-lightweight-nas --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Zerocost Proxies For Lightweight Nas?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Zerocost Proxies For Lightweight Nas
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-zerocost-proxies-for-lightweight-nas/badge)](https://www.skillsdirectory.com/skills/hiyenwong-zerocost-proxies-for-lightweight-nas)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Zero-Cost Proxies for Lightweight NAS

**arXiv ID:** 2101.08134
**Authors:** Mohamed S. Abdelfattah, Abhinav Mehrotra, Łukasz Dudziak, Nicholas D. Lane
**Published:** 2021-01-20T13:59:52Z
**Abstract:**
Neural Architecture Search (NAS) is quickly becoming the standard methodology to design neural network models. However, NAS is typically compute-intensive because multiple models need to be evaluated before choosing the best one. To reduce the computational power and time needed, a proxy task is often used for evaluating each model instead of full training. In this paper, we evaluate conventional reduced-training proxies and quantify how well they preserve ranking between multiple models during search when compared with the rankings produced by final trained accuracy. We propose a series of zero-cost proxies, based on recent pruning literature, that use just a single minibatch of training data to compute a model's score. Our zero-cost proxies use 3 orders of magnitude less computation but can match and even outperform conventional proxies. For example, Spearman's rank correlation coefficient between final validation accuracy and our best zero-cost proxy on NAS-Bench-201 is 0.82, compared to 0.61 for EcoNAS (a recently proposed reduced-training proxy). Finally, we use these zero-cost proxies to enhance existing NAS search algorithms such as random search, reinforcement learning, evolutionary search and predictor-based search. For all search methodologies and across three different NAS datasets, we are able to significantly improve sample efficiency, and thereby decrease computation, by using our zero-cost proxies. For example on NAS-Bench-101, we achieved the same accuracy 4$\times$ quicker than the best previous result. Our code is made public at: https://github.com/mohsaied/zero-cost-nas.

## Skill Description

This skill is generated from the arXiv paper: Zero-Cost Proxies for Lightweight NAS (2101.08134).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2101.08134](http://arxiv.org/abs/2101.08134v2)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.