Papers › EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search

EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search

16 Feb 2021arXiv:2102.08099archive 2025-07-28

Vasco Lopes, Saeid Alirezazadeh, Luís A. Alexandre

Neural Architecture Search (NAS) has shown excellent results in designing architectures for computer vision problems. NAS alleviates the need for human-defined settings by automating architecture design and engineering. However, NAS methods tend to be slow, as they require large amounts of GPU computation. This bottleneck is mainly due to the performance estimation strategy, which requires the evaluation of the generated architectures, mainly by training them, to update the sampler method. In this paper, we propose EPE-NAS, an efficient performance estimation strategy, that mitigates the problem of evaluating networks, by scoring untrained networks and creating a correlation with their trained performance. We perform this process by looking at intra and inter-class correlations of an untrained network. We show that EPE-NAS can produce a robust correlation and that by incorporating it into a simple random sampling strategy, we are able to search for competitive networks, without requiring any training, in a matter of seconds using a single GPU. Moreover, EPE-NAS is agnostic to the search method, since it focuses on the evaluation of untrained networks, making it easy to integrate into almost any NAS method.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 3 code samples harvested from 1 repository linked to this paper: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 3 ran (1 with no instrument failure; 2 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

VascoLopes/EPENAS officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
VascoLopes/EPE-NAS officialmentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified 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

3 samples harvested: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
1ran; the contract check could not run

Licence: 0 of the 3 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 VascoLopes/EPE-NAS. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

VascoLopes/EPE-NAS official repository 3 samples, 3 ran (2 instrument-failed) · 0 unverified
eval_score search.py ran · honoured contract fingerprinted MIT (permissive) · 5819779af11c2caf · report fixture: signature jacob:ndarray/2/float, labels:NoneType/0/?, n_classes:int/0/int · returned float64 · level recorded 2026-09-22
eval_score_perclass search.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 78fdf3831a585295 · report fixture: signature jacob:ndarray/2/float, labels:ndarray/2/int, n_classes:int/0/int · returned float64 · level recorded 2026-09-22
get_batch_jacobian search.py ran · our draft was wrong MIT (permissive) · 271a1e01e67260a2 · report fixture: signature net:callable/0/?, x:Tensor/2/float, target:Tensor/1/int, to:str/0/str, device:device/0/?, args:NoneType/0/? · returned tuple · level recorded 2026-09-22

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, CIFAR-10 EPE-NAS (N=10) Accuracy (Test) 92.63 #28 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 EPE-NAS (N=10) Accuracy (Val) 89.90 #28 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 EPE-NAS (N=10) Search time (s) 2.3 #28 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 EPE-NAS (N=500) Accuracy (Test) 92.27 #29 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 EPE-NAS (N=500) Accuracy (Val) 88.17 #29 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 EPE-NAS (N=500) Search time (s) 105.8 #29 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 EPE-NAS (N=100) Accuracy (Test) 91.59 #30 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 EPE-NAS (N=100) Accuracy (Val) 88.74 #30 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 EPE-NAS (N=100) Search time (s) 20.5 #30 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 EPE-NAS (N=1000) Accuracy (Test) 91.31 #31 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 EPE-NAS (N=1000) Accuracy (Val) 87.87 #31 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-10 EPE-NAS (N=1000) Search time (s) 206.2 #31 of 37 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 EPE-NAS (N=10) Accuracy (Test) 70.10 #27 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 EPE-NAS (N=10) Accuracy (Val) 69.78 #27 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 EPE-NAS (N=10) Search time (s) 2.3 #27 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 EPE-NAS (N=1000) Accuracy (Test) 69.58 #28 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 EPE-NAS (N=1000) Accuracy (Val) 69.44 #28 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 EPE-NAS (N=1000) Search time (s) 206.2 #28 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 EPE-NAS (N=500) Accuracy (Test) 69.33 #31 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 EPE-NAS (N=500) Accuracy (Val) 69.23 #31 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 EPE-NAS (N=500) Search time (s) 105.8 #31 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 EPE-NAS (N=100) Accuracy (Test) 67.19 #32 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 EPE-NAS (N=100) Accuracy (Val) 67.28 #32 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, CIFAR-100 EPE-NAS (N=100) Search time (s) 20.5 #32 of 40 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 EPE-NAS (N=500) Accuracy (Test) 42.05 #33 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 EPE-NAS (N=500) Search time (s) 105.8 #33 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 EPE-NAS (N=10) Accuracy (Test) 41.92 #34 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 EPE-NAS (N=10) Search time (s) 2.3 #34 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 EPE-NAS (N=1000) Accuracy (Test) 41.84 #35 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 EPE-NAS (N=1000) Search time (s) 206.2 #35 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 EPE-NAS (N=100) Accuracy (Test) 38.80 #38 of 49 Archive leaderboard report
Neural Architecture Search NAS-Bench-201, ImageNet-16-120 EPE-NAS (N=100) Search time (s) 20.5 #38 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.

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