Research map / Optimization / Distributed and compressed
Error feedback theory
Analyze error feedback mechanisms for compressed distributed optimization.
17 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2018–2026) · an approach in Distributed and compressed, keyword cluster “communication distributed · gradient compression · error feedback”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
5 papers in 2023–24 and 5 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic held steady, from 7.0% to 6.7%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2018 · Communication Compression for Decentralized Training (NeurIPS 2018 · 179 citations)
- 2021 · EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback (NeurIPS 2021 · 36 citations)
- 2022 · EF-BV: A Unified Theory of Error Feedback and Variance Reduction Mechanisms for Biased and Unbiased Compression in Distributed Optimization (NeurIPS 2022 · 3 citations)
- 2023 · Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top (ICLR 2023 · 5 citations)
- 2024 · EControl: Fast Distributed Optimization with Compression and Error Control (ICLR 2024 · 1 citation)
- 2025 · Accelerated Methods with Compressed Communications for Distributed Optimization Problems Under Data Similarity (AAAI 2025 · 0 citations)
- 2026 · A Tight Theory of Error Feedback Algorithms in Distributed Optimization (ICML 2026 · 0 citations)
Earliest papers here
- Communication Compression for Decentralized Training (NeurIPS 2018 · 179 citations)
- EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback (NeurIPS 2021 · 36 citations)
- Step-Ahead Error Feedback for Distributed Training with Compressed Gradient (AAAI 2021 · 12 citations)
What has been tried
15 papers here report 125 measured changes (a component added, removed or swapped, compared with a baseline): helped 64%, no clear effect 14%, hurt 18%, mixed 3%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Set η=1 instead of controlling the error-compensation feedback strength | Toy example · stability | Hurt | EControl: Fast Distributed Optimization with Compression and Error Control (ICLR 2024 · 1 citation) | |
| add random reshuffling to DIANA without adding per-example shifts | mushrooms, w8a, and a9a · functional suboptimality | No clear effect | Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences (NeurIPS 2024 · 0 citations) | |
| Increase the number of workers | Humanoid Robot Fleet · convergence performance | Helped | Safe-EF: Error Feedback for Non-smooth Constrained Optimization (ICML 2025) |
What reviewers will expect
Datasets and baselines named in the 5 papers of this approach from 2024–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- a9a · 2 of 5 papers
- mushrooms · 2 of 5 papers
- CIFAR-10 · 2 of 5 papers
Baselines
- EF21 · 3 of 5 papers
- CGD · 2 of 5 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 10 papers; from OpenAlex and the papers' affiliations).
- King Abdullah University of Science and Technology · 3 papers
- Mohamed bin Zayed University of Artificial Intelligence · 2 papers
- University of Basel · 2 papers
- ETHZ - ETH Zurich · 2 papers
Use it
Download BibTeX of 17 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Gradient quantization and sparsification (57 papers)
- Communication complexity theory (35 papers)
Elsewhere in the topic
- Decentralized optimization algorithms (94 papers)
- Local and asynchronous SGD (84 papers)
- Byzantine-robust learning (32 papers)
- Compressed distributed optimization (30 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).