Papers › Theory-Inspired Path-Regularized Differential Network Architecture Search

Theory-Inspired Path-Regularized Differential Network Architecture Search

30 Jun 2020NeurIPS 2020 12arXiv:2006.16537archive 2025-07-28

Pan Zhou, Caiming Xiong, Richard Socher, Steven C. H. Hoi

Despite its high search efficiency, differential architecture search (DARTS) often selects network architectures with dominated skip connections which lead to performance degradation. However, theoretical understandings on this issue remain absent, hindering the development of more advanced methods in a principled way. In this work, we solve this problem by theoretically analyzing the effects of various types of operations, e.g. convolution, skip connection and zero operation, to the network optimization. We prove that the architectures with more skip connections can converge faster than the other candidates, and thus are selected by DARTS. This result, for the first time, theoretically and explicitly reveals the impact of skip connections to fast network optimization and its competitive advantage over other types of operations in DARTS. Then we propose a theory-inspired path-regularized DARTS that consists of two key modules: (i) a differential group-structured sparse binary gate introduced for each operation to avoid unfair competition among operations, and (ii) a path-depth-wise regularization used to incite search exploration for deep architectures that often converge slower than shallow ones as shown in our theory and are not well explored during the search. Experimental results on image classification tasks validate its advantages.

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="2006.16537")

Code

Syntology Ran 1 of 6 code samples harvested from 1 repository linked to this paper; 5 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: community (archive-listed): 6 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.

salesforce/PR-DARTS 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

6 samples harvested; 1 ran; 0 honoured the contract we drafted; 5 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
5unverified

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 salesforce/PR-DARTS. “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.

adjust_lr salesforce/PR-DARTS/PRDARTS_eval/train_imagenet.py community (archive-listed) ran MIT (permissive) · e7ef53e9c5847e3e · report
accuracy salesforce/PR-DARTS/PRDARTS_eval/utils.py community (archive-listed) unverified MIT (permissive) · 469bf48752905889 · report
change_key salesforce/PR-DARTS/PRDARTS_search/get_cell_based_tiny_net.py community (archive-listed) unverified MIT (permissive) · 11f5fc83cf977b27 · report
count_parameters_in_MB salesforce/PR-DARTS/PRDARTS_eval/utils.py community (archive-listed) unverified MIT (permissive) · 3e816289579cc9e9 · report
drop_path salesforce/PR-DARTS/PRDARTS_eval/utils.py community (archive-listed) unverified MIT (permissive) · 13c2719404e25b25 · report
parse_channel_info salesforce/PR-DARTS/PRDARTS_search/get_cell_based_tiny_net.py community (archive-listed) unverified MIT (permissive) · d5744b71dab29e1e · report

Tasks

Image Classificationimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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