Pith. sign in

REVIEW 7 cited by

On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.04723 v1 pith:YNAKXV2R submitted 2022-06-09 cs.LG

classification cs.LG
keywords fedavgdatafederateddissimilaritygradientheterogeneitytheoreticalalgorithm
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Existing theory predicts that data heterogeneity will degrade the performance of the Federated Averaging (FedAvg) algorithm in federated learning. However, in practice, the simple FedAvg algorithm converges very well. This paper explains the seemingly unreasonable effectiveness of FedAvg that contradicts the previous theoretical predictions. We find that the key assumption of bounded gradient dissimilarity in previous theoretical analyses is too pessimistic to characterize data heterogeneity in practical applications. For a simple quadratic problem, we demonstrate there exist regimes where large gradient dissimilarity does not have any negative impact on the convergence of FedAvg. Motivated by this observation, we propose a new quantity, average drift at optimum, to measure the effects of data heterogeneity, and explicitly use it to present a new theoretical analysis of FedAvg. We show that the average drift at optimum is nearly zero across many real-world federated training tasks, whereas the gradient dissimilarity can be large. And our new analysis suggests FedAvg can have identical convergence rates in homogeneous and heterogeneous data settings, and hence, leads to better understanding of its empirical success.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression

    cs.LG 2025-01 conditional novelty 8.0 of 10

    A two-stage Local GD with learning-rate warmup achieves O(1/(K R)) convergence for heterogeneous distributed logistic regression, proving that local steps can provably reduce communication rounds.

  2. What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity

    cs.LG 2026-07 conditional novelty 7.0 of 10

    Local SGD provably improves over Mini-batch SGD under bounded second-order heterogeneity in the general convex setting, with nearly tight upper and lower bounds.

  3. Constant Stepsize Local GD for Logistic Regression: Acceleration by Instability

    cs.LG 2025-06 conditional novelty 7.0 of 10

    For separable logistic regression, Local GD with any step size and any communication interval converges at rate O~(1/(eta K R)) after O~(eta K M) unstable rounds, beating the general O(1/R) worst-case bound.

  4. Federated Learning from Molecules to Processes: A Perspective

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Federated learning lets chemical companies train shared models on private data, and two case studies show it approaches centralized accuracy while outperforming isolated training.

  5. Task Arithmetic Through The Lens Of One-Shot Federated Learning

    cs.LG 2024-11 conditional novelty 5.0 of 10

    Task arithmetic is exactly one-shot FedAvg with outer step size beta = lambda T, and FedNova, FedGMA, Median, and CCLIP can often improve merged model performance.

  6. What Makes Local Updates Effective: The Role of Data Heterogeneity and Smoothness

    cs.LG 2025-06 conditional novelty 4.0 of 10

    Under bounded second-order heterogeneity, local updates are shown to achieve faster convergence than mini-batch SGD in several convex and non-convex regimes, with matching lower bounds.

  7. How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy

    cs.CR 2025-12 conditional novelty 2.0 of 10

    A practical, extremely thorough survey of differentially private synthetic data generation: methods, privacy units, evaluation metrics, and end-to-end system components across four data modalities.

Pith tools