# Trainless Model Performance Estimation for Neural Architecture Search

Source: [Trainless Model Performance Estimation for Neural Architecture Search](<https://www.sota2.com/research/paper/68fa6af01e209131cea2b366>)

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

Data updated: 2025-10-27T06:10:35.496Z

Authors: Ekaterina Gracheva

Published: 2021-03-10T06:20:27.000Z

## Abstract

Neural architecture search has become an indispensable part of the deep learning field. Modern methods allow to find one of the best performing architectures, or to build one from scratch, but they typically make decisions based on the trained accuracy information. In the present article we explore instead how the architectural component of a neural network affects its prediction power. We focus on relationships between the trained accuracy of an architecture and its accuracy prior to training, by considering statistics over multiple initialisations. We observe that minimising the coefficient of variation of the untrained accuracy, $CV\_{U}$, consistently leads to better performing architectures. We test the $CV\_{U}$ as a neural architecture search scoring metric using the NAS-Bench-201 database of trained neural architectures. The architectures with the lowest $CV\_{U}$ value have on average an accuracy of $91.90 \\pm 2.27$, $64.08 \\pm 5.63$ and $38.76 \\pm 6.62$ for CIFAR-10, CIFAR-100 and a downscaled version of ImageNet, respectively. Since these values are statistically above the random baseline, we make a conclusion that a good architecture should be stable against weights initialisations. It takes about $190$ s for CIFAR-10 and CIFAR-100 and $133.9$ s for ImageNet16-120 to process $100$ architectures, on a batch of $256$ images, with $100$ initialisations.

## 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/2103.08312>)

[PDF](<https://arxiv.org/pdf/2103.08312.pdf>)
