SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.16537 · NeurIPS · 2020

Theory-Inspired Path-Regularized Differential Network Architecture Search

Richard Socher, Steven Hoi, Pan Zhou, Caiming Xiong

arXiv · PDF · Open in the Atlas

Code that ran

3 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2006.16537.json · badge: /api/ran/2006.16537.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
salesforce/PR-DARTS community (classifier label)
classifier basis not recorded on the link
3 ran · 3 no recorded run
FunctionStatusWhere it lives
adjust_lr Ran
ran, honoured the contract we drafted
salesforce/PR-DARTS/PRDARTS_eval/train_imagenet.py
pointer only (licence: MIT); the stored copy get_code serves, from chenxin061/pdarts, is pointer only (licence: NOASSERTION) · get_code("e7ef53e9c5847e3e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from chenxin061/pdarts, and GitHub could not classify the licence of that repository (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

change_key Ran
ran on a synthesized input
salesforce/PR-DARTS/PRDARTS_search/get_cell_based_tiny_net.py
code served (permissive licence) · get_code("11f5fc83cf977b27")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function change_key takes a key (string) and value (any type)
# and returns a function that sets that attribute on modules
# The returned function is typically used with module.apply()

class SimpleModule(nn.Module):
    def __init__(self):
        super().__init__()
        self.weight = torch.randn(2, 3)
        self.bias = torch.randn(4)
        self.custom_attr = "old_value"

# Create a test module
module = SimpleModule()

# Define arguments for change_key function
# key: the attribute name to change
# value: the new value to set for that attribute
key_arg = "custom_attr"
value_arg = "new_value"

ARGS = {
    "key": key_arg,
    "value": value_arg
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
parse_channel_info Ran
ran on a synthesized input
salesforce/PR-DARTS/PRDARTS_search/get_cell_based_tiny_net.py
code served (permissive licence) · get_code("d5744b71dab29e1e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

def parse_channel_info(xstring):
    blocks = xstring.split(' ')
    blocks = [x.split('-') for x in blocks]
    blocks = [[int(_) for _ in x] for x in blocks]
    return blocks

ARGS = {
    'xstring': '1-2-3 4-5 6-7-8-9'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list — a list output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
accuracy Not yet run
unverified (harvested, no recorded run)
salesforce/PR-DARTS/PRDARTS_eval/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from yuxwind/exactcompression, is pointer only (licence: NONE) · get_code("469bf48752905889")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from yuxwind/exactcompression, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

count_parameters_in_MB Not yet run
unverified (harvested, no recorded run)
salesforce/PR-DARTS/PRDARTS_eval/utils.py
code served (permissive licence) · get_code("3e816289579cc9e9")
How it ran

no invocation recorded.

drop_path Not yet run
unverified (harvested, no recorded run)
salesforce/PR-DARTS/PRDARTS_eval/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from hyeonjeongha/croze, is pointer only (licence: NONE) · get_code("13c2719404e25b25")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from hyeonjeongha/croze, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 6 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 6 later) and 0 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
accuracy 71 other papers
29 dated earlier, 5 the same month, 37 later · 2 only as an assembly brick
1505.05424 (2015-05)
Weight Uncertainty in Neural Networks
1705.07204 (2017-05)
Ensemble Adversarial Training: Attacks and Defenses
1802.10399 (2018-02)
Compressing Neural Networks using the Variational Information Bottleneck
and 68 more not named here
adjust_lr 8 other papers
5 dated earlier, 3 later
1806.09055 (2018-06)
DARTS: Differentiable Architecture Search
1904.12760 (2019-04)
Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluation
1906.07528 (2019-06)
Prune and Replace NAS
and 5 more not named here
count_parameters_in_MB 8 other papers
3 dated earlier, 5 later
1806.09055 (2018-06)
DARTS: Differentiable Architecture Search
1912.00195 (2019-12)
SGAS: Sequential Greedy Architecture Search
2004.14557 (2020-04)
Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond
and 5 more not named here
drop_path 6 other papers
2 dated earlier, 4 later
1806.09055 (2018-06)
DARTS: Differentiable Architecture Search
1912.00195 (2019-12)
SGAS: Sequential Greedy Architecture Search
2007.03154 (2020-07)
Discretization-Aware Architecture Search
and 3 more not named here
change_key 2 other papers
2 later
2108.11939 (2021-08)
Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics
parse_channel_info 2 other papers
2 later
2108.11939 (2021-08)
Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metrics

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 search. Experimental results on image classification tasks validate its advantages. 34th Conference on Neural Information Processing Systems (NeurIPS 2020),

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2006.16537")
get_code_for_paper("2006.16537")
have("2006.16537")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2006.16537.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2006.16537.svg)](https://syntology.ai/paper/2006.16537)

Connect an agent — have() is free.