SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.13819 · ICLR · 2021

MULTI-LEVEL LOCAL SGD: DISTRIBUTED SGD FOR HETEROGENEOUS HIERARCHICAL NETWORKS

Timothy Castiglia, Anirban Das, Stacy Patterson

arXiv · PDF · Open in the Atlas

Code that ran

10 of 17 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; 3 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 5 failures of our instrument; 7 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/2007.13819.json · badge: /api/ran/2007.13819.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
rpi-nsl/mll-sgd canonical (classifier label)
classifier basis: classifier_2025
2 ran · 2 no recorded run
rpi-nsl/MLL-SGD marked official in Papers with Code
Papers with Code archive
8 ran · 5 no recorded run
FunctionStatusWhere it lives
CIFARNet Ran
ran on a synthesized input
rpi-nsl/MLL-SGD/mll_sgd.py
pointer only (licence: NONE) · get_code("2be8f1fd1d0126f9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/MLL-SGD 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. A run is recorded.

average_nns Ran
ran; our contract draft was wrong, not the code
rpi-nsl/MLL-SGD/mll_sgd.py
pointer only (licence: NONE) · get_code("01bbc9cd2edd7ae8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/MLL-SGD 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. A run is recorded.

average_regs Ran
ran, honoured the contract we drafted
rpi-nsl/MLL-SGD/mll_sgd.py
pointer only (licence: NONE) · get_code("33dc8373c3463f42")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/MLL-SGD 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. A run is recorded.

cNet Ran
ran on a synthesized input
rpi-nsl/MLL-SGD/mll_sgd.py
pointer only (licence: NONE) · get_code("b19f7ac37a874a5e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/MLL-SGD 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. A run is recorded.

federated_sets Ran
ran; our contract draft was wrong, not the code
rpi-nsl/MLL-SGD/mll_sgd.py
pointer only (licence: NONE) · get_code("280eb93b728aaac1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/MLL-SGD 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. A run is recorded.

fit_nn Ran
ran; our contract draft was wrong, not the code
rpi-nsl/MLL-SGD/mll_sgd.py
pointer only (licence: NONE) · get_code("a69ca357a6c2bf2e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/MLL-SGD 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. A run is recorded.

get_client_epochs Ran
ran, honoured the contract we drafted
rpi-nsl/MLL-SGD/mll_sgd.py
pointer only (licence: NONE) · get_code("4cd836ab934f29d6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/MLL-SGD 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. A run is recorded.

initializeNN Ran
ran; our contract draft was wrong, not the code
rpi-nsl/MLL-SGD/mll_sgd.py
pointer only (licence: NONE) · get_code("952d6442a35e3056")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/MLL-SGD 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. A run is recorded.

sigmoid Ran
ran, honoured the contract we drafted
rpi-nsl/mll-sgd/mll_sgd.py
pointer only (licence: NONE) · get_code("c803a6bd4c1c93ac")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/mll-sgd 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. A run is recorded.

stagger_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rpi-nsl/mll-sgd/plot_exps.py
pointer only (licence: NONE) · get_code("d9ff6fea347fd10d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/mll-sgd 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. A run is recorded.

accuracy_nn Not yet run
unverified (harvested, no recorded run)
rpi-nsl/MLL-SGD/mll_sgd.py
pointer only (licence: NONE) · get_code("5fed0f8e6ceb9928")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/MLL-SGD 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.

accuracy_reg Not yet run
unverified (harvested, no recorded run)
rpi-nsl/MLL-SGD/mll_sgd.py
pointer only (licence: NONE) · get_code("d224f3d2d98c7990")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/MLL-SGD 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.

client Not yet run
unverified (harvested, no recorded run)
rpi-nsl/MLL-SGD/mll_sgd.py
pointer only (licence: NONE) · get_code("183961204c88619c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/MLL-SGD 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.

cost_nn Not yet run
unverified (harvested, no recorded run)
rpi-nsl/mll-sgd/mll_sgd.py
pointer only (licence: NONE) · get_code("8edeb8f58c7c948a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/mll-sgd 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.

cost_reg Not yet run
unverified (harvested, no recorded run)
rpi-nsl/mll-sgd/mll_sgd.py
pointer only (licence: NONE) · get_code("4c7a836df096acbd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/mll-sgd 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.

fed_hierarchy Not yet run
unverified (harvested, no recorded run)
rpi-nsl/MLL-SGD/mll_sgd.py
pointer only (licence: NONE) · get_code("41d4d49fea66a5a7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/MLL-SGD 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.

fit_reg Not yet run
unverified (harvested, no recorded run)
rpi-nsl/MLL-SGD/mll_sgd.py
pointer only (licence: NONE) · get_code("d31f3868ce25073d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, rpi-nsl/MLL-SGD 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 16 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
sigmoid
brick of this paper's assembly: helper
7 other papers
1 dated earlier, 6 later
2006.06887 (2020-06)
Stochastic Optimization for Performative Prediction
2207.09176 (2022-07)
Self-Supervision Can Be a Good Few-Shot Learner
2402.14992 (2024-02)
tinyBenchmarks: evaluating LLMs with fewer examples
and 4 more not named here

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

We propose Multi-Level Local SGD, a distributed stochastic gradient method for learning a smooth, non-convex objective in a multi-level communication network with heterogeneous workers. Our network model consists of a set of disjoint subnetworks, with a single hub and multiple workers; further, workers may have different operating rates. The hubs exchange information with one another via a connected, but not necessarily complete, communication network. In our algorithm, sub-networks execute a distributed SGD algorithm, using a hub-and-spoke paradigm, and the hubs periodically average their models with neighboring hubs. We first provide a unified mathematical framework that describes the Multi-Level Local SGD algorithm. We then present a theoretical analysis of the algorithm; our analysis shows the dependence of the convergence error on the worker node heterogeneity, hub network topology, and the number of local, sub-network, and global iterations. We illustrate the effectiveness of our algorithm in a multi-level network with slow workers via simulation-based experiments.

For agents

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

get_harvested_code_for_paper("2007.13819")
get_code_for_paper("2007.13819")
have("2007.13819")

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

curl https://syntology.ai/api/ran/2007.13819.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.13819.svg)](https://syntology.ai/paper/2007.13819)

Connect an agent — have() is free.