Research map / Learning theory and algorithms / Sample complexity
Distributed Saddle-Point Problems Under Data Similarity
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 |
|---|---|---|---|
| Exploit similarity between local functions | Distributed saddle-point algorithms · Strongly-convex-strongly-concave SPP, master/workers | communication rounds: O(Δ (1 + δ/μ) log(1/ε)) versus O(L/μ · log(1/ε)) | Helped |
| Exploit similarity between local functions | Distributed saddle-point algorithms · Strongly-convex-strongly-concave SPP, mesh network | communication rounds: Õ(1/√ρ · (1 + δ/μ) log²(1/ε)) versus Ω(1/√ρ · (1 + δ/μ) · log(||z⁰ − z*||/ε)) | Helped |
| Use the Star Min-Max Data Similarity Algorithm instead of centralized Extragradient | Robust linear regression · Synthetic data, master/workers | communications to reach a given distance from solution | Helped |
| Increase noise in local datasets to amplitude 10.0 | Robust linear regression · Synthetic data, master/workers | communications to reach a given distance from solution | No clear effect |
| Increase the number of workers, reducing data similarity | Star Min-Max Data Similarity Algorithm · a9a dataset, master/workers | communications to reach a given distance from solution | Mixed |
Closest papers by meaning
- Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks (ICML 2017 · similarity 0.88)
- Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks (NeurIPS 2024 · similarity 0.87)
- On the Complexity of Finite-Sum Smooth Optimization under the Polyak–Łojasiewicz Condition (ICML 2024 · similarity 0.85)
- On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms (ICML 2025 · similarity 0.85)
- Accelerated Methods with Compressed Communications for Distributed Optimization Problems Under Data Similarity (AAAI 2025 · similarity 0.85)
- Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity (NeurIPS 2024 · 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.