Papers › sharpDARTS: Faster and More Accurate Differentiable Architecture Search

sharpDARTS: Faster and More Accurate Differentiable Architecture Search

23 Mar 2019arXiv:1903.09900archive 2025-07-28

Andrew Hundt, Varun Jain, Gregory D. Hager

Neural Architecture Search (NAS) has been a source of dramatic improvements in neural network design, with recent results meeting or exceeding the performance of hand-tuned architectures. However, our understanding of how to represent the search space for neural net architectures and how to search that space efficiently are both still in their infancy. We have performed an in-depth analysis to identify limitations in a widely used search space and a recent architecture search method, Differentiable Architecture Search (DARTS). These findings led us to introduce novel network blocks with a more general, balanced, and consistent design; a better-optimized Cosine Power Annealing learning rate schedule; and other improvements. Our resulting sharpDARTS search is 50% faster with a 20-30% relative improvement in final model error on CIFAR-10 when compared to DARTS. Our best single model run has 1.93% (1.98+/-0.07) validation error on CIFAR-10 and 5.5% error (5.8+/-0.3) on the recently released CIFAR-10.1 test set. To our knowledge, both are state of the art for models of similar size. This model also generalizes competitively to ImageNet at 25.1% top-1 (7.8% top-5) error. We found improvements for existing search spaces but does DARTS generalize to new domains? We propose Differentiable Hyperparameter Grid Search and the HyperCuboid search space, which are representations designed to leverage DARTS for more general parameter optimization. Here we find that DARTS fails to generalize when compared against a human's one shot choice of models. We look back to the DARTS and sharpDARTS search spaces to understand why, and an ablation study reveals an unusual generalization gap. We finally propose Max-W regularization to solve this problem, which proves significantly better than the handmade design. Code will be made available.

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="1903.09900")

Code

Syntology Ran 1 of 1 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 1 sample 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.

ahundt/sharpDARTS officialmentioned 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

1 sample harvested; 1 ran; 0 honoured the contract we drafted; 0 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

Licence: 0 of the 1 sample 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 ahundt/sharpDARTS. “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.

gen_greedy_path ahundt/sharpDARTS/cnn/train_search.py official repository ran · our draft was wrong Apache-2.0 (permissive) · bfa400764d6e3fa8 · report

Tasks

Hyperparameter OptimizationImage ClassificationNeural Architecture Search

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Neural Architecture Search CIFAR-10 SharpSepConvDARTS FLOPS 579M #6 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 SharpSepConvDARTS Parameters 3.6M #6 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 SharpSepConvDARTS Search Time (GPU days) 0.8 #6 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 SharpSepConvDARTS Top-1 Error Rate 1.98% #6 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 sharpDARTS FLOPS 357M #10 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 sharpDARTS Parameters 1.98M #10 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 sharpDARTS Search Time (GPU days) 1.8 #10 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 sharpDARTS Top-1 Error Rate 2.29% #10 of 41 Archive leaderboard report
Neural Architecture Search CIFAR-10 Image Classification SharpSepConvDARTS FLOPS 579M #4 of 19 Archive leaderboard report
Neural Architecture Search CIFAR-10 Image Classification SharpSepConvDARTS Params 3.6M #4 of 19 Archive leaderboard report
Neural Architecture Search CIFAR-10 Image Classification SharpSepConvDARTS Percentage error 1.98 #4 of 19 Archive leaderboard report
Neural Architecture Search ImageNet sharpDARTS Accuracy 76.0 #95 of 135 Archive leaderboard report
Neural Architecture Search ImageNet sharpDARTS MACs 950M #95 of 135 Archive leaderboard report
Neural Architecture Search ImageNet sharpDARTS Params 8.3M #95 of 135 Archive leaderboard report
Neural Architecture Search ImageNet sharpDARTS Top-1 Error Rate 24.0 #95 of 135 Archive leaderboard report
Neural Architecture Search ImageNet SharpSepConvDARTS Accuracy 74.1 #116 of 135 Archive leaderboard report
Neural Architecture Search ImageNet SharpSepConvDARTS MACs 573M #116 of 135 Archive leaderboard report
Neural Architecture Search ImageNet SharpSepConvDARTS Params 4.9M #116 of 135 Archive leaderboard report
Neural Architecture Search ImageNet SharpSepConvDARTS Top-1 Error Rate 25.1 #116 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

Introduced by this paper: Differentiable Hyperparameter Search

Cosine Power AnnealingDARTSDARTS Max-WDifferentiable Hyperparameter SearchExponential Decay

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