Research map / Graph learning / Graph algorithms and clustering
LDLE: Low Distortion Local Eigenmaps
Dhruv Kohli, Alexander Cloninger, Gal Mishne
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 the doubled-manifold distance matrix when boundary points are known (ablation) | LDLE local parameterization · Square grid | local distortion near boundary | Improved |
| increase eta_min to enlarge intermediate views (ablation) | LDLE clustering · Square grid | distortion of intermediate view parameterization | Hurt |
| add clustering into intermediate views before Procrustes registration (ablation) | LDLE · Square grid | registration speed and error | Improved |
| use different eigenvector sets per neighborhood instead of the first d eigenvectors (ablation) | local parameterization on unit square · Unit square | local distortion | Improved |
| replace LDLE alignment with LTSA alignment on the same intermediate views (ablation) | LDLE · Square grid and noisy data | embedding quality | Hurt |
| estimate gradient inner products by finite sum, Feynman-Kac or LLR (ablation) | LDLE · Square grid and Swiss Roll | estimation error | No clear effect |
Closest papers by meaning
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.88)
- The Noisy Laplacian: a Threshold Phenomenon for Non-Linear Dimension Reduction (ICML 2025 · similarity 0.87)
- Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding (NeurIPS 2023 · similarity 0.87)
- Recovering Manifold Structure Using Ollivier Ricci Curvature (ICLR 2025 · similarity 0.87)
- Graph Geometry-Preserving Autoencoders (ICML 2024 · similarity 0.85)
- Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional Data (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.
