Research map / Optimization / Distributed and compressed
Towards Optimal Communication Complexity in Distributed Non-Convex Optimization
Kumar Kshitij Patel, Lingxiao Wang, Blake Woodworth, Brian Bullins, Nathan Srebro
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 CE-LSGD with one lighter large-batch gradient instead of BVR-L-SGD's repeated heavy batches | CE-LSGD · CIFAR-10 heterogeneous, intermittent communication, M=10 | training loss vs communication rounds | Improved |
| compare CE-LSGD with BVR-L-SGD at convergence | CE-LSGD · CIFAR-10 heterogeneous | final training loss | No clear effect |
| compare CE-LSGD and BVR-L-SGD against FedAvg, SCAFFOLD, MB-SARAH, MB-SGD at equal updates | CE-LSGD · CIFAR-10, K=32, varying q | training loss | Improved |
| reduce heavy-batch size from BVR-L-SGD's to CE-LSGD's | CE-LSGD · Theory, full participation | heavy-batch ratio: <= 1 | Improved |
Closest papers by meaning
- Optimal Convergence Rates for Convex Distributed Optimization in Networks (JMLR 2019 · similarity 0.91)
- Communication Lower Bounds for Distributed Convex Optimization: Partition Data on Features (AAAI 2017 · similarity 0.91)
- On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization (NeurIPS 2024 · similarity 0.89)
- Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization (AAAI 2024 · similarity 0.89)
- Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity (NeurIPS 2024 · similarity 0.89)
- Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks (NeurIPS 2024 · similarity 0.89)
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.
