Papers › Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours

Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours

5 Apr 2019arXiv:1904.02877archive 2025-07-28

Dimitrios Stamoulis, Ruizhou Ding, Di Wang, Dimitrios Lymberopoulos, Bodhi Priyantha, Jie Liu, Diana Marculescu

Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the runtime constraint of a mobile device? Neural architecture search (NAS) has revolutionized the design of hardware-efficient ConvNets by automating this process. However, the NAS problem remains challenging due to the combinatorially large design space, causing a significant searching time (at least 200 GPU-hours). To alleviate this complexity, we propose Single-Path NAS, a novel differentiable NAS method for designing hardware-efficient ConvNets in less than 4 hours. Our contributions are as follows: 1. Single-path search space: Compared to previous differentiable NAS methods, Single-Path NAS uses one single-path over-parameterized ConvNet to encode all architectural decisions with shared convolutional kernel parameters, hence drastically decreasing the number of trainable parameters and the search cost down to few epochs. 2. Hardware-efficient ImageNet classification: Single-Path NAS achieves 74.96% top-1 accuracy on ImageNet with 79ms latency on a Pixel 1 phone, which is state-of-the-art accuracy compared to NAS methods with similar constraints (<80ms). 3. NAS efficiency: Single-Path NAS search cost is only 8 epochs (30 TPU-hours), which is up to 5,000x faster compared to prior work. 4. Reproducibility: Unlike all recent mobile-efficient NAS methods which only release pretrained models, we open-source our entire codebase at: https://github.com/dstamoulis/single-path-nas.

PaperPDFCodeCode 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="1904.02877")

Code

Syntology Ran 1 of 16 code samples harvested from 1 repository linked to this paper; 15 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: official repository: 16 samples from 1 repository, 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.

dstamoulis/single-path-nas officialmentioned in papermentioned on GitHubtfApache-2.0 report
osmr/imgclsmob mentioned on GitHubmxnetMIT 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

16 samples harvested; 1 ran; 1 honoured the contract we drafted; 15 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 · honoured contract
15unverified

Licence: 0 of the 16 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 dstamoulis/single-path-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. “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.

round_filters dstamoulis/single-path-nas/nas-search/singlepath_supernet.py official repository ran · honoured contract Apache-2.0 (permissive) · 285e4d1d9a3faeba · report
Indicator dstamoulis/single-path-nas/nas-search/superkernel.py official repository unverified Apache-2.0 (permissive) · 43e89725b46a75d5 · report
build_dropout_rate dstamoulis/single-path-nas/nas-search/nas_utils.py official repository unverified Apache-2.0 (permissive) · 3ea91536d334ba52 · report
build_learning_rate dstamoulis/single-path-nas/nas-search/nas_utils.py official repository unverified Apache-2.0 (permissive) · 713b0060c42cdcd3 · report
build_runtime_lambda dstamoulis/single-path-nas/nas-search/nas_utils.py official repository unverified Apache-2.0 (permissive) · bbafe1b852b9e3f6 · report
conv_kernel_initializer dstamoulis/single-path-nas/nas-search/singlepath_supernet.py official repository unverified Apache-2.0 (permissive) · 17a1e9aed5cc4cee · report
convnet_encoder dstamoulis/single-path-nas/nas-search/plot-progress/parse_search_output.py official repository unverified Apache-2.0 (permissive) · 146419f540edce62 · report
dense_kernel_initializer dstamoulis/single-path-nas/nas-search/singlepath_supernet.py official repository unverified Apache-2.0 (permissive) · e430f1fd246b1b51 · report
distorted_bounding_box_crop dstamoulis/single-path-nas/nas-search/preprocessing.py official repository unverified Apache-2.0 (permissive) · f45ff6307a313357 · report
encode_single_path_nas_arch dstamoulis/single-path-nas/nas-search/plot-progress/parse_search_output.py official repository unverified Apache-2.0 (permissive) · 0ff5f3be7fcd4b71 · report
export dstamoulis/single-path-nas/nas-search/search_main.py official repository unverified Apache-2.0 (permissive) · e75aa2c199a09405 · report
parse_indicators_single_path_nas dstamoulis/single-path-nas/nas-search/plot-progress/parse_search_output.py official repository unverified Apache-2.0 (permissive) · 0ee0acc6ddbf5670 · report
preprocess_for_eval dstamoulis/single-path-nas/nas-search/preprocessing.py official repository unverified Apache-2.0 (permissive) · 3a458358e2a9447b · report
preprocess_for_train dstamoulis/single-path-nas/nas-search/preprocessing.py official repository unverified Apache-2.0 (permissive) · bc13cc6b340f0924 · report
round_filters dstamoulis/single-path-nas/runtime-modeling/model_def.py official repository unverified Apache-2.0 (permissive) · 7d1529c236ba14b5 · report
sample_gumbel dstamoulis/single-path-nas/nas-search/superkernel.py official repository unverified Apache-2.0 (permissive) · fdd42e9c322647b8 · report

Tasks

General ClassificationImage ClassificationNeural Architecture Searchimage-classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet Single-Path NAS Top 1 Accuracy 74.96% #963 of 1060 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

1x1 ConvolutionAverage PoolingBatch NormalizationConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDifferentiable NASGlobal Average PoolingInverted Residual BlockPointwise ConvolutionSingle-path NASSoftmax

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