Papers › Neural Architecture Search without Training

Neural Architecture Search without Training

8 Jun 2020arXiv:2006.04647archive 2025-07-28

Joseph Mellor, Jack Turner, Amos Storkey, Elliot J. Crowley

The time and effort involved in hand-designing deep neural networks is immense. This has prompted the development of Neural Architecture Search (NAS) techniques to automate this design. However, NAS algorithms tend to be slow and expensive; they need to train vast numbers of candidate networks to inform the search process. This could be alleviated if we could partially predict a network's trained accuracy from its initial state. In this work, we examine the overlap of activations between datapoints in untrained networks and motivate how this can give a measure which is usefully indicative of a network's trained performance. We incorporate this measure into a simple algorithm that allows us to search for powerful networks without any training in a matter of seconds on a single GPU, and verify its effectiveness on NAS-Bench-101, NAS-Bench-201, NATS-Bench, and Network Design Spaces. Our approach can be readily combined with more expensive search methods; we examine a simple adaptation of regularised evolutionary search. Code for reproducing our experiments is available at https://github.com/BayesWatch/nas-without-training.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2006.04647")

Code

Syntology Ran 3 of 10 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run. Of those that ran: 3 ran · our draft was wrong.

By repository: community (archive-listed): 9 samples from 2 repositories, 2 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

BayesWatch/nas-without-training officialmentioned in papermentioned on GitHubpytorch report
idstcv/ZenNAS mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 3 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · our draft was wrong
7unverified

Licence: 3 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

compute_nas_score idstcv/ZenNAS/ZeroShotProxy/compute_zen_score.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 866a541b53979f13 · report
network_weight_gaussian_init idstcv/ZenNAS/ZeroShotProxy/compute_zen_score.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 28d3ae653452ecdf · report
compute_centered_ranks nlinc1905/evolutionary-reinforcement-learner/utils.py community (archive-listed) unverified MIT (permissive) · 693ed9995a4ce7ea · report
get_mean_and_standardized_rewards nlinc1905/evolutionary-reinforcement-learner/utils.py community (archive-listed) unverified MIT (permissive) · 3817dba1742caf11 · report
mutate nlinc1905/evolutionary-reinforcement-learner/utils.py community (archive-listed) unverified MIT (permissive) · 91e7124a049d07e9 · report
quadratic_fxn_fitness nlinc1905/evolutionary-reinforcement-learner/reward_functions/fitness_functions.py community (archive-listed) unverified MIT (permissive) · acf41416a7469905 · report
relu nlinc1905/evolutionary-reinforcement-learner/models/mlp.py community (archive-listed) unverified MIT (permissive) · 0bd581e0afb4c04a · report
softmax nlinc1905/evolutionary-reinforcement-learner/models/mlp.py community (archive-listed) unverified MIT (permissive) · 2374481500fc132c · report
train_function_optimizing_agent nlinc1905/evolutionary-reinforcement-learner/examples.py community (archive-listed) unverified MIT (permissive) · 248ec46cc977d5ae · report
get_flop_loss identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · 5aa7497aa00af169 · report

Tasks

Neural Architecture Search

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 NAS without training (N=10) Accuracy (Test) 38.33 #39 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 NAS without training (N=10) Search time (s) 1.7 #39 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 NAS without training (N=100) Accuracy (Test) 36.37 #40 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 NAS without training (N=100) Search time (s) 17.4 #40 of 49 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

LSTMSigmoid ActivationSoftmaxTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections