Research map / Bandits and online learning / Online convex optimization and games
Projection-free Distributed Online Learning in Networks
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 |
|---|---|---|---|
| replace projection with linear optimization step (conditional gradient) in distributed online learning | D-OCG vs D-OGD and D-ODA · multiclass classification on two LIBSVM datasets, complete graph with 9 nodes | running time to reach average loss | Helped |
| use distributed online conditional gradient (D-OCG) instead of centralized OCG with 1 node | D-OCG · multiclass classification, complete graph | average loss | No clear effect |
| increase network size (complete graphs with more nodes) | D-OCG · aloi, complete graphs with varying node count | average loss decrease speed | Hurt |
| improve graph connectivity (complete, Watts-Strogatz, cycle at 16 nodes) (ablation) | D-OCG · aloi, 16 nodes | convergence speed of average loss | Helped |
Closest papers by meaning
- Non-stationary Projection-Free Online Learning with Dynamic and Adaptive Regret Guarantees (AAAI 2024 · similarity 0.87)
- Revisiting Differentially Private Algorithms for Decentralized Online Learning (ICML 2025 · similarity 0.85)
- Revisiting Projection-Free Online Learning with Time-Varying Constraints (AAAI 2025 · similarity 0.85)
- A Simple and Optimal Approach for Universal Online Learning with Gradient Variations (NeurIPS 2024 · similarity 0.84)
- Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence (AAAI 2025 · similarity 0.84)
- AdaGK-SGD: Adaptive Global Knowledge Guided Distributed Stochastic Gradient Descent (AAAI 2025 · similarity 0.84)
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.