# Neural Architecture Search: Two Constant Shared Weights Initialisations

Source: [Neural Architecture Search: Two Constant Shared Weights Initialisations](<https://www.sota2.com/research/paper/68fa79d31e209131cea7f8e6>)

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

Data updated: 2025-10-26T05:06:33.533Z

Authors: Ekaterina Gracheva

Published: 2023-02-09T02:25:38.000Z

## Abstract

In the last decade, zero-cost metrics have gained prominence in neural architecture search (NAS) due to their ability to evaluate architectures without training. These metrics are significantly faster and less computationally expensive than traditional NAS methods and provide insights into neural architectures' internal workings. This paper introduces epsinas, a novel zero-cost NAS metric that assesses architecture potential using two constant shared weight initialisations and the statistics of their outputs. We show that the dispersion of raw outputs, normalised by their average magnitude, strongly correlates with trained accuracy. This effect holds across image classification and language tasks on NAS-Bench-101, NAS-Bench-201, and NAS-Bench-NLP. Our method requires no data labels, operates on a single minibatch, and eliminates the need for gradient computation, making it independent of training hyperparameters, loss metrics, and human annotations. It evaluates a network in a fraction of a GPU second and integrates seamlessly into existing NAS frameworks. The code supporting this study can be found on GitHub at https://github.com/egracheva/epsinas.

## 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/2302.04406>)

[PDF](<https://arxiv.org/pdf/2302.04406.pdf>)
