Research map / Optimization / Distributed and compressed
DINGO: Distributed Newton-Type Method for Gradient-Norm Optimization
Rixon Crane, Fred Roosta
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 |
|---|---|---|---|
| Move the workers from one node to AWS instances | DINGO · EMNIST Digits | iterations completed in one hour: 8 -> 12; +50% | Improved |
| Move the workers from one node to AWS instances | GIANT · EMNIST Digits | iterations completed in one hour: 11 -> 18; +64% | Improved |
| Move the workers from one node to AWS instances | DiSCO · EMNIST Digits | iterations completed in one hour: 23 -> 19; -17% | Hurt |
| Move the workers from one node to AWS instances | InexactDANE · EMNIST Digits | iterations completed in one hour: 593 -> 486; -18% | Hurt |
| Move the workers from one node to AWS instances | AIDE · EMNIST Digits | iterations completed in one hour: 601 -> 486; -19% | Hurt |
| Move the workers from one node to AWS instances | Sync-SGD · EMNIST Digits | iterations completed in one hour: 6003 -> 1187; -80% | Hurt |
| Increase theta from 10^-4 to 1 or 100 (ablation) | DINGO · EMNIST Digits | gradient norm reduction | Hurt |
| Increase theta from 10^-4 to 1 or 100 (ablation) | DINGO · EMNIST Digits | objective value convergence | No clear effect |
Later papers that compared with this method
1 later accepted paper reports DINGO as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- DINO: Distributed Newton-Type Optimization Method (ICML 2020 · better on 0 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DINO: Distributed Newton-Type Optimization Method (ICML 2020 · similarity 0.91)
- Optimal Convergence Rates for Convex Distributed Optimization in Networks (JMLR 2019 · similarity 0.89)
- Communication-Efficient Distributed Optimization with Quantized Preconditioners (ICML 2021 · similarity 0.89)
- Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers (ICML 2024 · similarity 0.86)
- Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence (AAAI 2025 · similarity 0.86)
- Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity (NeurIPS 2024 · similarity 0.86)
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.
