SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2108.08842 · ICML · 2022

EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning

Amit Portnoy, Gal Mendelson, Yaniv Ben-Itzhak, Michael Mitzenmacher, Shay Vargaftik, Ran Basat

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 0 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2108.08842.json · badge: /api/ran/2108.08842.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
amitport/eden-distributed-mean-estimation canonical (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
FunctionStatusWhere it lives
gen_boundaries Ran
ran, violated the contract we drafted
amitport/eden-distributed-mean-estimation/tf/eden.py
pointer only (licence: NONE) · get_code("8dc106217c4fa287")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, amitport/eden-distributed-mean-estimation 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.

bernoulli_mask Ran
ran; our contract draft was wrong, not the code
amitport/eden-distributed-mean-estimation/torch/eden.py
pointer only (licence: NONE) · get_code("e5439bcacd6ae1a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, amitport/eden-distributed-mean-estimation 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.

mask_combine Ran
ran; our contract draft was wrong, not the code
amitport/eden-distributed-mean-estimation/torch/eden.py
pointer only (licence: NONE) · get_code("d601bb2886264245")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, amitport/eden-distributed-mean-estimation 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.

mask_split Ran
ran; our contract draft was wrong, not the code
amitport/eden-distributed-mean-estimation/torch/eden.py
pointer only (licence: NONE) · get_code("3104ed431dab1ef9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, amitport/eden-distributed-mean-estimation 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

Distributed Mean Estimation (DME) is a central building block in federated learning, where clients send local gradients to a parameter server for averaging and updating the model. Due to communication constraints, clients often use lossy compression techniques to compress the gradients, resulting in estimation inaccuracies. DME is more challenging when clients have diverse network conditions, such as constrained communication budgets and packet losses. In such settings, DME techniques often incur a significant increase in the estimation error leading to degraded learning performance. In this work, we propose a robust DME technique named EDEN that naturally handles heterogeneous communication budgets and packet losses. We derive appealing theoretical guarantees for EDEN and evaluate it empirically. Our results demonstrate that EDEN consistently improves over state-of-the-art DME techniques.

For agents

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

get_harvested_code_for_paper("2108.08842")
get_code_for_paper("2108.08842")
have("2108.08842")

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

curl https://syntology.ai/api/ran/2108.08842.json

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

[![Syntology run record](https://syntology.ai/api/ran/2108.08842.svg)](https://syntology.ai/paper/2108.08842)

Connect an agent — have() is free.