SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.00295 · ICLR · 2021

Adaptive Federated Optimization

Sanjiv Kumar, Manzil Zaheer, Sashank Reddi, Zachary Charles, Zachary Garrett, Keith Rush, Jakub Konečný, H Mcmahan

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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, 0 violated it and 0 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-21; 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/2003.00295.json · badge: /api/ran/2003.00295.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
vaseline555/Federated-Learning-in-PyTorch community (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
FunctionStatusWhere it lives
stratified_split Ran
ran; our contract draft was wrong, not the code
vaseline555/Federated-Learning-in-PyTorch/src/utils.py
code served (permissive licence) · get_code("11666a4ae1749613")
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 tuple. 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 random
import numpy as np
from torch.utils.data import Dataset, Subset

torch.manual_seed(0)
random.seed(0)

class DummyDataset(Dataset):
    def __init__(self, num_samples=10, num_classes=3):
        self.data = torch.randn(num_samples, 4)
        self.targets = torch.randint(0, num_classes, (num_samples,))
    
    def __len__(self):
        return len(self.data)
    
    def __getitem__(self, idx):
        return self.data[idx], self.targets[idx]

# Create a base dataset
base_dataset = DummyDataset(num_samples=10, num_classes=3)

# Create a Subset of the base dataset (simulating raw_dataset)
subset_indices = list(range(10))
raw_dataset = Subset(base_dataset, subset_indices)

# Add the dataset and indices attributes that stratified_split expects
raw_dataset.dataset = base_dataset
raw_dataset.indices = subset_indices

test_size = 0.3

ARGS = {
    "raw_dataset": raw_dataset,
    "test_size": test_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple 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
check_args Not yet run
unverified (harvested, no recorded run)
vaseline555/Federated-Learning-in-PyTorch/src/utils.py
code served (permissive licence) · get_code("26d709a4649d9aea")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 1 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
stratified_split 1 other paper
1 later
2405.20821 (2024-05)
Pursuing Overall Welfare in Federated Learning through Sequential Decision Making

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Federated learning is a distributed machine learning paradigm in which a large number of clients coordinate with a central server to learn a model without sharing their own training data. Standard federated optimization methods such as Federated Averaging (FEDAVG) are often difficult to tune and exhibit unfavorable convergence behavior. In non-federated settings, adaptive optimization methods have had notable success in combating such issues. In this work, we propose federated versions of adaptive optimizers, including ADAGRAD, ADAM, and YOGI, and analyze their convergence in the presence of heterogeneous data for general nonconvex settings. Our results highlight the interplay between client heterogeneity and communication efficiency. We also perform extensive experiments on these methods and show that the use of adaptive optimizers can significantly improve the performance of federated learning.

For agents

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

get_harvested_code_for_paper("2003.00295")
get_code_for_paper("2003.00295")
have("2003.00295")

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

curl https://syntology.ai/api/ran/2003.00295.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.00295.svg)](https://syntology.ai/paper/2003.00295)

Connect an agent — have() is free.