Research map / Learning theory and algorithms / Sample complexity
Nearly Optimal Robust Subspace Tracking
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 NORST's recursive projected compressive sensing and iterative SVD subspace updates | RST · RST under Theorem 1 assumptions | tracking delay: O(r \log n \log(1/\epsilon)) | Helped |
| Use NORST rather than s-ReProCS | RST · RST | tracking delay: r-times sub-optimal | Helped |
| Allow mild subspace changes without restricting each change to one direction | NORST · RST | subspace change model flexibility | Helped |
| Bound outlier frequency per row over each update interval instead of imposing a moving-object support model | NORST · RST after initialization | outlier tolerance: O(1) | Helped |
| Process data offline after subspace estimation | NORST · Dynamic RPCA | normalized recovery error: \varepsilon | Helped |
Closest papers by meaning
- Implicit Bias of Projected Subgradient Method Gives Provable Robust Recovery of Subspaces of Unknown Codimension (ICLR 2022 · similarity 0.88)
- Dual Principal Component Pursuit for Robust Subspace Learning: Theory and Algorithms for a Holistic Approach (ICML 2021 · similarity 0.87)
- Outlier-Robust Sparse Estimation via Non-Convex Optimization (NeurIPS 2022 · similarity 0.87)
- A Subspace-Constrained Tyler's Estimator and its Applications to Structure from Motion (CVPR 2024 · similarity 0.87)
- Global Convergence of Adaptive Sensing for Principal Eigenvector Estimation (ICML 2026 · similarity 0.87)
- Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery (ICML 2025 · 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.