Research map / Learning theory and algorithms / Matrix and tensor methods
Outlier-Robust High-Dimensional Sparse Estimation via Iterative Filtering
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 |
|---|---|---|---|
| Use RME_sp instead of RANSAC | Robust sparse mean estimation · Synthetic constant-biased, linear-hiding, and flipping noise | ℓ2 error to the true mean | Helped |
| Add the quadratic filter to the linear-filter-only variant (ablation) | RME_sp · Synthetic linear-hiding noise | ℓ2 error to the true mean | Helped |
| Use only the linear filter, removing the quadratic filter (ablation) | RME_sp · Synthetic linear-hiding noise | ℓ2 error to the true mean: ε√k | Hurt |
| Use the full RME_sp filtering method rather than the linear-filter-only variant (ablation) | Robust sparse mean estimation · Synthetic constant-biased noise | ℓ2 error to the true mean | No clear effect |
| Use RME_sp instead of RME | Robust sparse mean estimation · Synthetic sparse-mean experiments | runtime | Helped |
| Use RSPCA instead of RDPCA | Robust sparse PCA · Synthetic spiked-covariance data, k < √d | estimation error | Helped |
| Use RSPCA instead of RDPCA | Robust sparse PCA · Synthetic spiked-covariance data, k greater than roughly √d | estimation error | Hurt |
Closest papers by meaning
- Outlier-Robust Sparse Estimation via Non-Convex Optimization (NeurIPS 2022 · similarity 0.95)
- A Subquadratic Time Algorithm for Robust Sparse Mean Estimation (ICML 2024 · similarity 0.92)
- High-dimensional Robust Mean Estimation via Gradient Descent (ICML 2020 · similarity 0.91)
- Robust Sparse Estimation for Gaussians with Optimal Error under Huber Contamination (ICML 2024 · similarity 0.90)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · similarity 0.87)
- Fast and Provable Algorithms for Sparse PCA with Improved Sample Complexity (ICML 2025 · similarity 0.87)
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.