Papers › Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective

Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective

23 Feb 2021ICLR 2021 1arXiv:2102.11535archive 2025-07-28

Wuyang Chen, Xinyu Gong, Zhangyang Wang

Neural Architecture Search (NAS) has been explosively studied to automate the discovery of top-performer neural networks. Current works require heavy training of supernet or intensive architecture evaluations, thus suffering from heavy resource consumption and often incurring search bias due to truncated training or approximations. Can we select the best neural architectures without involving any training and eliminate a drastic portion of the search cost? We provide an affirmative answer, by proposing a novel framework called training-free neural architecture search (TE-NAS). TE-NAS ranks architectures by analyzing the spectrum of the neural tangent kernel (NTK) and the number of linear regions in the input space. Both are motivated by recent theory advances in deep networks and can be computed without any training and any label. We show that: (1) these two measurements imply the trainability and expressivity of a neural network; (2) they strongly correlate with the network's test accuracy. Further on, we design a pruning-based NAS mechanism to achieve a more flexible and superior trade-off between the trainability and expressivity during the search. In NAS-Bench-201 and DARTS search spaces, TE-NAS completes high-quality search but only costs 0.5 and 4 GPU hours with one 1080Ti on CIFAR-10 and ImageNet, respectively. We hope our work inspires more attempts in bridging the theoretical findings of deep networks and practical impacts in real NAS applications. Code is available at: https://github.com/VITA-Group/TENAS.

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="2102.11535")

Code

Syntology Ran 2 of 4 code samples harvested from 3 repositories linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it.

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

VITA-Group/TENAS officialmentioned in papermentioned on GitHubpytorch report
idstcv/ZenNAS mentioned on GitHubpytorch report
pnnl/torchntk mentioned on GitHubpytorch report
vita-group/tegnas mentioned on GitHubpytorchMIT 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

4 samples harvested; 2 ran; 0 honoured the contract we drafted; 2 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.

1ran · our draft was wrong
1ran · fixture could not drive it
2unverified

Licence: 2 of the 4 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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.

cal_entropy VITA-Group/TENAS/lib/models/cell_searchs/search_model_darts.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 5adedaaf29d0048f · report
get_ntk_n VITA-Group/TENAS/lib/procedures/ntk.py official repository unverified MIT (permissive) · 16d05701e6a4d833 · report
autograd_ntk pnnl/torchntk/torchntk/autograd/autograd_ntk.py community (archive-listed) ran · fixture could not drive it licence not identified · pointer only · 8c9e2a9cf3c22af1 · report
get_ntk_n idstcv/ZenNAS/ZeroShotProxy/compute_te_nas_score.py community (archive-listed) unverified no licence file found · pointer only · 943299cba82721a7 · 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 NATS-Bench Topology, CIFAR-10 TE-NAS (Chen et al., 2021) Test Accuracy 93.90 #4 of 11 Archive leaderboard report
Neural Architecture Search NATS-Bench Topology, CIFAR-100 TE-NAS (Chen et al., 2021) Test Accuracy 71.24 #5 of 11 Archive leaderboard report
Neural Architecture Search NATS-Bench Topology, ImageNet16-120 TE-NAS (Chen et al., 2021) Test Accuracy 42.38 #6 of 11 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

DARTS

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