mlsanityData to 14 Oct 2026

Distributed Fixed Point Methods with Compressed Iterates

arXiv 1912.09925 ↗First posted 20 Dec 2019cs.LG cs.DC cs.NAcited by 11

Not on the map. Why?

Abstract (arXiv)

We propose basic and natural assumptions under which iterative optimization methods with compressed iterates can be analyzed. This problem is motivated by the practice of federated learning, where a large model stored in the cloud is compressed before it is sent to a mobile device, which then proceeds with training based on local data. We develop standard and variance reduced methods, and establish communication complexity bounds. Our algorithms are the first distributed methods with compressed iterates, and the first fixed point methods with compressed iterates.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). First posted on arXiv 20 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 4; 2023: 3; 2024: 1; 2025: 2.

11 papers.

  1. 2023DoCoFL: Downlink Compression for Cross-Device Federated Learningcited by 28
  2. 2021Partial Variable Training for Efficient On-Device Federated Learningcited by 14
  3. 2022Federated Random Reshuffling with Compression and Variance Reductioncited by 12
  4. 2023Improving Accelerated Federated Learning with Compression and Importance Samplingcited by 8
  5. 2022Online Model Compression for Federated Learning with Large Modelscited by 7
  6. 2022Shifted Compression Framework: Generalizations and Improvementscited by 6
  7. 2022Personalized Federated Learning with Communication Compressioncited by 6
  8. 2023Towards a Better Theoretical Understanding of Independent Subnetwork Trainingcited by 6
  9. 2024Local Methods with Adaptivity via Scalingcited by 1
  10. 2025Tight analyses of first-order methods with error feedbackcited by 1
  11. 2025First Provable Guarantees for Practical Private FL: Beyond Restrictive Assumptionscited by 1