# Probabilistic Neural Architecture Search

Source: [Probabilistic Neural Architecture Search](<https://www.sota2.com/research/paper/68fa65671e209131cea0a111>)

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

Data updated: 2025-10-25T21:25:53.160Z

Authors: Francesco Paolo Casale, Jonathan Gordon, Nicolo Fusi

Published: 2019-02-13T20:38:18.000Z

## Abstract

In neural architecture search (NAS), the space of neural network architectures is automatically explored to maximize predictive accuracy for a given task. Despite the success of recent approaches, most existing methods cannot be directly applied to large scale problems because of their prohibitive computational complexity or high memory usage. In this work, we propose a Probabilistic approach to neural ARchitecture SEarCh (PARSEC) that drastically reduces memory requirements while maintaining state-of-the-art computational complexity, making it possible to directly search over more complex architectures and larger datasets. Our approach only requires as much memory as is needed to train a single architecture from our search space. This is due to a memory-efficient sampling procedure wherein we learn a probability distribution over high-performing neural network architectures. Importantly, this framework enables us to transfer the distribution of architectures learnt on smaller problems to larger ones, further reducing the computational cost. We showcase the advantages of our approach in applications to CIFAR-10 and ImageNet, where our approach outperforms methods with double its computational cost and matches the performance of methods with costs that are three orders of magnitude larger.

## 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.

- [Image Classification on ImageNet Mobile Setting (test)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-mobile-setting-test.md>): Image Classification; ImageNet Mobile Setting (test); Top-1 Error: 26.

- [Image Classification on ImageNet (test)](<https://www.sota2.com/research/sota/image-classification-on-imagenet-test.md>): Image Classification; ImageNet (test); Top-1 Acc: not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1902.05116>)

[PDF](<https://arxiv.org/pdf/1902.05116.pdf>)
