Papers › Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis

Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis

11 May 2022arXiv:2205.05662archive 2025-07-28

Wuyang Chen, Wei Huang, Xinyu Gong, Boris Hanin, Zhangyang Wang

Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex. Diverse operations are connected by complicated connectivity patterns, e.g., various types of skip connections. Those topological compositions are empirically effective and observed to smooth the loss landscape and facilitate the gradient flow in general. However, it remains elusive to derive any principled understanding of their effects on the DNN capacity or trainability, and to understand why or in which aspect one specific connectivity pattern is better than another. In this work, we theoretically characterize the impact of connectivity patterns on the convergence of DNNs under gradient descent training in fine granularity. By analyzing a wide network's Neural Network Gaussian Process (NNGP), we are able to depict how the spectrum of an NNGP kernel propagates through a particular connectivity pattern, and how that affects the bound of convergence rates. As one practical implication of our results, we show that by a simple filtration on "unpromising" connectivity patterns, we can trim down the number of models to evaluate, and significantly accelerate the large-scale neural architecture search without any overhead. Code is available at: https://github.com/VITA-Group/architecture_convergence.

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="2205.05662")

Code

Syntology Ran 6 of 21 code samples harvested from 2 repositories linked to this paper; 15 have no recorded run. Of those that ran: 2 ran · violated contract; 3 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 21 samples from 2 repositories, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

chenwydj/architecture_convergence officialmentioned in papermentioned on GitHubpytorchMIT report
vita-group/architecture_convergence officialmentioned in papermentioned 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

21 samples harvested; 6 ran; 0 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.

2ran · violated contract
3ran · our draft was wrong
1ran
15unverified

Licence: 0 of the 21 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; 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.

calculate_md5 chenwydj/architecture_convergence/nas-without-training/datasets/DownsampledImageNet.py official repository ran · our draft was wrong MIT (permissive) · ad0636a128295d5a · report
check_md5 chenwydj/architecture_convergence/nas-without-training/datasets/DownsampledImageNet.py official repository ran · violated contract MIT (permissive) · 380a00b777aad655 · report
check_integrity chenwydj/architecture_convergence/nas-without-training/datasets/DownsampledImageNet.py official repository ran · violated contract fingerprinted MIT (permissive) · e947a6effcaaf32b · report
format_time chenwydj/architecture_convergence/mlp_code/utils.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 8d7ec010c29e813b · report
get_flop_loss VITA-Group/architecture_convergence/nas-without-training/autodl/procedures/search_main.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 5aa7497aa00af169 · report
get_mean_and_std chenwydj/architecture_convergence/mlp_code/utils.py official repository ran · metamorphic tier: well formed MIT (permissive) · 3cbdd3b190b16350 · report
accuracy chenwydj/architecture_convergence/mlp_code/utils.py official repository unverified MIT (permissive) · fce4d8316ff3d185 · report
edge2value chenwydj/architecture_convergence/nas-without-training/collect_arch_data.py official repository unverified MIT (permissive) · d9b7f522f765561e · report
find_all_paths chenwydj/architecture_convergence/nas-without-training/collect_arch_data.py official repository unverified MIT (permissive) · c2c1522bfc9c4a8b · report
find_all_paths_3d_prob chenwydj/architecture_convergence/TENAS/prune_tenas.py official repository unverified MIT (permissive) · 5cc4e76addc371ea · report
get_batch_jacobian chenwydj/architecture_convergence/nas-without-training/score_networks.py official repository unverified MIT (permissive) · e7c03b50082d9c61 · report
get_cifar_test_loader chenwydj/architecture_convergence/mlp_code/dataset.py official repository unverified MIT (permissive) · 44f160db0172cb70 · report
get_score_func chenwydj/architecture_convergence/nas-without-training/scores.py official repository unverified MIT (permissive) · 16139ec12e4595a3 · report
get_svhn_test_loader chenwydj/architecture_convergence/mlp_code/dataset.py official repository unverified MIT (permissive) · aa037b9bfa339105 · report
hooklogdet chenwydj/architecture_convergence/nas-without-training/scores.py official repository unverified MIT (permissive) · 8d9701991ac208d4 · report
init_model chenwydj/architecture_convergence/TENAS/prune_tenas.py official repository unverified MIT (permissive) · e1591bd29b12e21d · report
make_colours_by_hue chenwydj/architecture_convergence/nas-without-training/plot_scores.py official repository unverified MIT (permissive) · 2cd6cda6c652de6d · report
prepare_logger chenwydj/architecture_convergence/mlp_code/logger.py official repository unverified MIT (permissive) · a87bbc139870cdc0 · report
random_score chenwydj/architecture_convergence/nas-without-training/scores.py official repository unverified MIT (permissive) · 3aa2047d05e1a518 · report
round_to chenwydj/architecture_convergence/TENAS/prune_tenas.py official repository unverified MIT (permissive) · 65d81629d7179cf5 · report
svhn_dataloaders chenwydj/architecture_convergence/mlp_code/dataset.py official repository unverified MIT (permissive) · cc11bb618b200b77 · report

Tasks

AutoMLNeural Architecture Search

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Gaussian Process

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