Papers › Towards modular and programmable architecture search

Towards modular and programmable architecture search

30 Sep 2019NeurIPS 2019 12arXiv:1909.13404archive 2025-07-28

Renato Negrinho, Darshan Patil, Nghia Le, Daniel Ferreira, Matthew Gormley, Geoffrey Gordon

Neural architecture search methods are able to find high performance deep learning architectures with minimal effort from an expert. However, current systems focus on specific use-cases (e.g. convolutional image classifiers and recurrent language models), making them unsuitable for general use-cases that an expert might wish to write. Hyperparameter optimization systems are general-purpose but lack the constructs needed for easy application to architecture search. In this work, we propose a formal language for encoding search spaces over general computational graphs. The language constructs allow us to write modular, composable, and reusable search space encodings and to reason about search space design. We use our language to encode search spaces from the architecture search literature. The language allows us to decouple the implementations of the search space and the search algorithm, allowing us to expose search spaces to search algorithms through a consistent interface. Our experiments show the ease with which we can experiment with different combinations of search spaces and search algorithms without having to implement each combination from scratch. We release an implementation of our language with this paper.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 2 repositories linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 3 samples from 1 repository, 1 ran (0 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 13 samples from 1 repository, 10 ran (10 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

negrinho/deep_architect officialmentioned in papermentioned on GitHubtfSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
negrinho/deep_architect_legacy mentioned on GitHubtfMITSyntology: 13 samples, 10 ran (0 instrument-failed) · 3 unverified 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: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
10ran
5unverified

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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

negrinho/deep_architect official repository 3 samples, 1 ran (1 instrument-failed) · 2 unverified
sorted_values_by_key deep_architect/core.py ran · our draft was wrong MIT (permissive) · 0fcde3f7818db7b9 · report fixture: signature d:dict/0/? · returned list · level recorded 2026-09-22
determine_module_eval_seq deep_architect/core.py unverified MIT (permissive) · 9c8caae33be86506 · report
extract_unique_modules deep_architect/core.py unverified MIT (permissive) · 4c8342e71f166f2b · report
negrinho/deep_architect_legacy community (archive-listed) 13 samples, 10 ran (0 instrument-failed) · 3 unverified
Optional_fn darch/modules.py ran MIT (permissive) · a23397aa96508c9e · report fixture: signature b:SimpleModule/0/? · returned Or · level recorded 2026-09-24
compute_padded_dims darch/modules.py ran MIT (permissive) · d77c894b8db356ad · report fixture: signature in_height:int/0/int, in_width:int/0/int, window_len:int/0/int, stride:int/0/int, padding:str/0/str · returned tuple · level recorded 2026-09-24
compute_percentiles plots.py ran fingerprinted MIT (permissive) · ff950237d4e1e5fd · report fixture: signature scores:list/1/float, thresholds:list/1/float · returned list · level recorded 2026-09-24
constant_initializer darch/initializers.py ran MIT (permissive) · 23308e943e627336 · report fixture: signature val:float/0/float · returned function · level recorded 2026-09-24
gaussian_initializer darch/initializers.py ran MIT (permissive) · 06396da2b2c2b8ad · report fixture: signature mean:float/0/float, stddev:float/0/float · returned function · level recorded 2026-09-24
load_mnist in 35 papers darch/datasets.py ran MIT (permissive) · a670d1a23a9c9041 · report fixture: signature data_dir:str/0/str, flatten:bool/0/bool, one_hot:bool/0/bool, normalize_range:bool/0/bool · returned tuple · level recorded 2026-09-24
onehot_to_idx darch/datasets.py ran fingerprinted MIT (permissive) · 863b33d3c3b063c5 · report fixture: signature y_onehot:ndarray/2/float · returned ndarray · level recorded 2026-09-24
propagate_seq darch/modules.py ran MIT (permissive) · 31baee2de886be6b · report fixture: signature bs:list/1/callable, i:int/0/int · returned int · level recorded 2026-09-24
running_max_stats plots.py ran fingerprinted MIT (permissive) · d3779a34252371e5 · report fixture: signature scores:ndarray/2/float · returned tuple · level recorded 2026-09-24
xavier_initializer_affine darch/initializers.py ran MIT (permissive) · 817a654081d21835 · report fixture: signature gain:float/0/float · returned function · level recorded 2026-09-24
deepconv_ss0 search_spaces.py unverified MIT (permissive) · 3dd086420646eb90 · report
resnet_ss0 search_spaces.py unverified MIT (permissive) · dc596d8ae84aa4d6 · report
tfref_convnet_ss0 search_spaces.py unverified MIT (permissive) · c16000cc3ab471b6 · report

Tasks

Hyperparameter OptimizationNeural Architecture Search

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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