Research map / Learning theory and algorithms / Matrix and tensor methods
Outlier Robust Mean Estimation with Subgaussian Rates via Stability
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 |
|---|---|---|---|
| Establish that a large inlier subset satisfies stability, then use a stability-based estimator | Robust mean estimation with bounded covariance under strong contamination · Strong contamination, bounded covariance | L2 mean estimation error: O(√((tr(Σ) log r(Σ))/n) + √(||Σ||ε) + √(||Σ||log(1/τ)/n)) | Helped |
| Add median-of-means preprocessing before the stability-based estimator | Robust mean estimation with bounded covariance under strong contamination · Strong contamination, bounded covariance | L2 mean estimation error: O(√(tr(Σ)/n) + √(||Σ||ε) + √(||Σ||log(1/τ)/n)) | Helped |
| Use bounded central-moment assumptions to obtain a sharper stability guarantee | Robust mean estimation with identity covariance · Strong contamination, bounded central moments | L2 mean estimation error: O(σ(√(d log d / n) + σ_k ε^{1 - 1/k} + σ_4√(log(1/τ)/n))) | Helped |
| Replace the prior filtering guarantee with the stability-based analysis | Robust mean estimation with bounded covariance · Strong contamination, bounded covariance | L2 mean estimation error: O(√ε + √(d log d /n)) -> O(√((tr(Σ) log r(Σ))/n) + √(||Σ||ε) + √(||Σ||log(1/τ)/n)) | Helped |
| Use median-of-means preprocessing | Stability-based robust mean estimation · Strong contamination, bounded covariance | L2 mean estimation error: O(√((tr(Σ) log r(Σ))/n) + √(||Σ||ε) + √(||Σ||log(1/τ)/n)) -> O(√(tr(Σ)/n) + √(||Σ||ε) + √(||Σ||log(1/τ)/n)) | Helped |
Closest papers by meaning
- A Subquadratic Time Algorithm for Robust Sparse Mean Estimation (ICML 2024 · similarity 0.88)
- Efficient Multivariate Robust Mean Estimation Under Mean-Shift Contamination (ICML 2025 · similarity 0.88)
- All-Purpose Mean Estimation over R: Optimal Sub-Gaussianity with Outlier Robustness and Low Moments Performance (ICML 2025 · similarity 0.86)
- Outlier-robust Kalman Filtering through Generalised Bayes (ICML 2024 · similarity 0.86)
- Robust Sparse Estimation for Gaussians with Optimal Error under Huber Contamination (ICML 2024 · similarity 0.86)
- Robust Estimation Under Heterogeneous Corruption Rates (NeurIPS 2025 · similarity 0.86)
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.