Research map / Learning theory and algorithms / Sample complexity
Distributed Gaussian Mean Estimation under Communication Constraints: Optimal Rates and Communication-Efficient Algorithms
T. Tony Cai, Hongji Wei
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 MODGAME instead of naive quantization | univariate Gaussian mean estimation · Simulation (d=1, m=100, sigma_n=2^-8, b 1 to 7) | MSE | Improved |
| use MODGAME instead of naive quantization with more machines | univariate Gaussian mean estimation · Simulation (b=5, m 10 to 40960) | MSE | Improved |
| use MODGAME instead of naive quantization at small noise | univariate Gaussian mean estimation · Simulation (b=5, m=100, sigma_n 2^-1 to 2^-13) | MSE | Improved |
| increase per-machine communication budget b | MODGAME · Simulation (d=1) | MSE | Improved |
| allocate total budget B unequally across machines instead of equally (ablation) | MODGAME · Simulation (m=6, sigma_n=2^-12, B 18 to 36) | MSE | No clear effect |
| increase per-machine budget b past 10 | multi-MODGAME · Simulation (d=50, m=25, sigma_n=2^-8, b 2 to 21) | MSE | Mixed |
Closest papers by meaning
- Optimal Sparsity-Sensitive Bounds for Distributed Mean Estimation (NeurIPS 2019 · similarity 0.89)
- Distributed Nonparametric Regression under Communication Constraints (ICML 2018 · similarity 0.89)
- Learning of Gaussian Processes in Distributed and Communication Limited Systems (TPAMI 2019 · similarity 0.88)
- Distributed Nonparametric Estimation: from Sparse to Dense Samples per Terminal (ICML 2025 · similarity 0.88)
- Correlated Quantization for Distributed Mean Estimation and Optimization (ICML 2022 · similarity 0.88)
- Fundamental Limits of Distributed Covariance Matrix Estimation Under Communication Constraints (ICML 2024 · similarity 0.85)
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.
