Research map / Graph learning / Graph algorithms and clustering
Perturbation Bounds for Procrustes, Classical Scaling, and Trilateration, with Applications to Manifold Learning
Ery Arias-Castro, Adel Javanmard, Bruno Pelletier
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 MVU instead of Isomap | Isomap · bent hypercube | embedding error d(Y,Z) | Improved |
| increase sample size n from 100 to 1000 (ablation) | Isomap · bent hypercube, d=2 | embedding error d(Y,Z): slope -0.50 | Improved |
| increase intrinsic dimension d from 2 to 15 (ablation) | Isomap · bent hypercube | error decay slope: -0.50 -> -0.08 | Hurt |
| increase intrinsic dimension d from 2 to 15 (ablation) | MVU · bent hypercube | error decay slope: -0.47 -> -0.04 | Hurt |
| change sampling dispersion sigma among 0.5, 1, 2 (ablation) | Isomap and MVU · Swiss Roll | error scaling: n^-1/2 scaling | No clear effect |
| increase singular values scale delta from 1 to 10 (ablation) | Procrustes · Procrustes simulation | ||Y-XQ|| | Improved |
Closest papers by meaning
- Estimation of Local Geometric Structure on Manifolds from Noisy Data (JMLR 2025 · similarity 0.86)
- Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy (NeurIPS 2025 · similarity 0.86)
- The Noisy Laplacian: a Threshold Phenomenon for Non-Linear Dimension Reduction (ICML 2025 · similarity 0.86)
- Perturbation Bounds for Low-Rank Inverse Approximations under Noise (NeurIPS 2025 · similarity 0.85)
- Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem (NeurIPS 2024 · similarity 0.85)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · 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.
