Papers › HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search

HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search

23 Feb 2021arXiv:2102.11646archive 2025-07-28

Niv Nayman, Yonathan Aflalo, Asaf Noy, Lihi Zelnik-Manor

Realistic use of neural networks often requires adhering to multiple constraints on latency, energy and memory among others. A popular approach to find fitting networks is through constrained Neural Architecture Search (NAS), however, previous methods enforce the constraint only softly. Therefore, the resulting networks do not exactly adhere to the resource constraint and their accuracy is harmed. In this work we resolve this by introducing Hard Constrained diffeRentiable NAS (HardCoRe-NAS), that is based on an accurate formulation of the expected resource requirement and a scalable search method that satisfies the hard constraint throughout the search. Our experiments show that HardCoRe-NAS generates state-of-the-art architectures, surpassing other NAS methods, while strictly satisfying the hard resource constraints without any tuning required.

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 6 code samples harvested from 2 repositories linked to this paper: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 2 samples from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 4 samples from 1 repository, 1 ran (1 with no instrument failure; 0 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.

Alibaba-MIIL/HardCoReNAS officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
alibaba-miil/binas mentioned on GitHubpytorchSyntology: 4 samples, 1 ran (0 instrument-failed) · 3 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

6 samples harvested: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 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.

2ran · honoured contract
4unverified

Licence: 0 of the 6 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

Alibaba-MIIL/HardCoReNAS official repository 2 samples, 1 ran (0 instrument-failed) · 1 unverified
calculate_temperature search.py ran · honoured contract fingerprinted MIT (permissive) · 622a379ad7dd9222 · report fixture: signature t:float/0/float, T0:float/0/float, Tf:float/0/float, tf:float/0/float, policy:str/0/str · returned float · level recorded 2026-09-22
argmax_attention search.py unverified MIT (permissive) · 4239d29f3166f205 · report
alibaba-miil/binas community (archive-listed) 4 samples, 1 ran (0 instrument-failed) · 3 unverified
smallest_sol search.py ran · honoured contract MIT (permissive) · 5992f0ad22591cd9 · report fixture: signature anames:list/1/str, bnames:list/1/str · returned tuple · level recorded 2026-09-22
get_train_val_dir search.py unverified MIT (permissive) · 957b3d09c343c5b3 · report
optimize_diff_predictor search.py unverified MIT (permissive) · 94d498c319661873 · report
validate in 313 papers accuracy_contribution.py unverified MIT (permissive) · 398498f4381620e6 · report

Tasks

Neural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search ImageNet HardcoreNAS_E_KD Accuracy 80.1 #21 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_E_KD MACs 330M #21 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_E_KD Top-1 Error Rate 19.9 #21 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_D_KD Accuracy 79.5 #31 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_D_KD MACs 290M #31 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_D_KD Top-1 Error Rate 20.5 #31 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_C_KD Accuracy 78.9 #40 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_C_KD MACs 270M #40 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_C_KD Top-1 Error Rate 21.1 #40 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_B_KD Accuracy 78.8 #41 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_B_KD MACs 250M #41 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_B_KD Top-1 Error Rate 21.2 #41 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_A_KD Accuracy 78.3 #50 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_A_KD MACs 220M #50 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_A_KD Top-1 Error Rate 21.7 #50 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_F Accuracy 78.1 #52 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_F MACs 340M #52 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_F Top-1 Error Rate 21.9 #52 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_E Accuracy 77.9 #56 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_E MACs 330M #56 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_E Top-1 Error Rate 22.1 #56 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_D Accuracy 77.4 #65 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_D MACs 290M #65 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_D Top-1 Error Rate 22.6 #65 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_C Accuracy 77.1 #74 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_C MACs 270M #74 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_C Top-1 Error Rate 22.9 #74 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_B Accuracy 76.5 #85 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_B MACs 250M #85 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_B Top-1 Error Rate 23.5 #85 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_A Accuracy 75.9 #101 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_A MACs 220M #101 of 135 Archive leaderboard report
Neural Architecture Search ImageNet HardcoreNAS_A Top-1 Error Rate 24.1 #101 of 135 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

Differentiable NAS

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