Research map / Optimization / Distributed and compressed
Communication-Efficient Frank-Wolfe Algorithm for Nonconvex Decentralized Distributed Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DQSFW instead of DeFW or QFW | Decentralized low-rank matrix completion · MovieLens 100k and MovieLens 1m | training loss versus bits transferred | Helped |
| Increase the number of workers | DQSFW · MovieLens 100k and MovieLens 1m | competitiveness against baselines | Helped |
| Use DQSFW instead of DeFW or QFW | VGG11 compression on CIFAR 10 · CIFAR 10 | training loss versus bits transferred | Helped |
| Use DQSFW instead of QFW | VGG11 compression on CIFAR 10 · CIFAR 10 | training loss versus time | No clear effect |
| Use gradient tracking to reach consensus on gradients | Decentralized quantized Frank-Wolfe · Nonconvex constrained optimization | convergence to a stationary point | Helped |
| Use vanilla decentralized quantized stochastic Frank-Wolfe without gradient tracking | Decentralized quantized Frank-Wolfe · Nonconvex constrained optimization | convergence | Hurt |
Closest papers by meaning
- Robust and Communication-Efficient Collaborative Learning (NeurIPS 2019 · similarity 0.90)
- Distributed Optimization for Overparameterized Problems: Achieving Optimal Dimension Independent Communication Complexity (NeurIPS 2022 · similarity 0.90)
- Improving the Sample and Communication Complexity for Decentralized Non-Convex Optimization: Joint Gradient Estimation and Tracking (ICML 2020 · similarity 0.89)
- BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression (NeurIPS 2022 · similarity 0.89)
- Towards Faster Decentralized Stochastic Optimization with Communication Compression (ICLR 2025 · similarity 0.88)
- Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features (ICML 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.