Research map / Optimization / Nonconvex and smooth optimization
IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method
Yossi Arjevani, Joan Bruna, Bugra Can, Mert Gurbuzbalaban, Stefanie Jegelka, Hongzhou Lin
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 MIDEAL in the low communication cost regime | Decentralized optimization · MNIST two-class logistic regression, low communication cost | log suboptimality over time | Improved |
| Use IDEAL in the high communication cost regime | Decentralized optimization · MNIST two-class logistic regression, high communication cost | log suboptimality over time | Improved |
| Increase inner-loop iterations beyond T=1 (ablation) | IDEAL · Further experimental results | stability | Improved |
| Set the inner-loop iteration count to T=1 (ablation) | IDEAL · Further experimental results | stability | Hurt |
Closest papers by meaning
- Decentralized Accelerated Proximal Gradient Descent (NeurIPS 2020 · similarity 0.88)
- Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization (NeurIPS 2020 · similarity 0.88)
- Decentralized Gradient-Free Methods for Stochastic Non-smooth Non-convex Optimization (AAAI 2024 · similarity 0.88)
- A Linearly Convergent Proximal Gradient Algorithm for Decentralized Optimization (NeurIPS 2019 · similarity 0.88)
- Linear Convergent Decentralized Optimization with Compression (ICLR 2021 · similarity 0.87)
- Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints (NeurIPS 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.
