Research map / Learning theory and algorithms / Matrix and tensor methods
High-dimensional Robust Mean Estimation via Gradient Descent
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 the softmax objective instead of the spectral norm objective | Projected gradient descent for robust mean estimation · High-dimensional robust mean estimation | iterations: \widetilde{O}(N^2d^4) -> \widetilde O(N d^3 / \ensuremath{\epsilon}\xspace) | Helped |
| Use the softmax objective instead of the spectral norm objective | Projected gradient descent for robust mean estimation · High-dimensional robust mean estimation | ℓ2 mean-estimation error | No clear effect |
Closest papers by meaning
- Outlier-Robust Sparse Estimation via Non-Convex Optimization (NeurIPS 2022 · similarity 0.92)
- Outlier Robust Mean Estimation with Subgaussian Rates via Stability (NeurIPS 2020 · similarity 0.92)
- Outlier-Robust High-Dimensional Sparse Estimation via Iterative Filtering (NeurIPS 2019 · similarity 0.91)
- A Subquadratic Time Algorithm for Robust Sparse Mean Estimation (ICML 2024 · similarity 0.89)
- Adversarial Robustness of Nonparametric Regression (NeurIPS 2025 · similarity 0.87)
- Consistent Adversarially Robust Linear Classification: Non-Parametric Setting (ICML 2024 · 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.