Research map / Learning theory and algorithms / Sample complexity
Communication-efficient distributed eigenspace estimation with arbitrary node failures
Vasileios Charisopoulos, Anil Damle
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 a robust reference estimator and adaptive filtering instead of the first response as reference followed by naive averaging | Distributed PCA · Gaussian simulation with adversarial node responses | subspace distance | Improved |
| Add robust mean estimation after Procrustes alignment (ablation) | ProcrustesFixing · Gaussian simulation with adversarial node responses | subspace distance | Improved |
| Use the proposed robust estimator with corruption level up to 45% | Distributed PCA · Gaussian simulation with adversarial node responses | subspace distance | Improved |
Closest papers by meaning
- Fundamental Limits of Distributed Covariance Matrix Estimation Under Communication Constraints (ICML 2024 · similarity 0.85)
- Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means (NeurIPS 2025 · similarity 0.83)
- Robust Estimation Under Heterogeneous Corruption Rates (NeurIPS 2025 · similarity 0.83)
- Exact Community Recovery under Side Information: Optimality of Spectral Algorithms (ICLR 2025 · similarity 0.82)
- Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization (ICLR 2024 · similarity 0.82)
- Coded Computing for Resilient Distributed Computing: A Learning-Theoretic Framework (NeurIPS 2024 · similarity 0.82)
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.
