Research map / Learning theory and algorithms / Optimal transport
Dimensionality Reduction has Quantifiable Imperfections: Two Geometric Bounds
Kry Lui, Gavin Weiguang Ding, Ruitong Huang, Robert McCann
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 |
|---|---|---|---|
| Reduce intrinsic dimension from n to m < n with a continuous map | Dimensionality reduction maps · Information retrieval on an n-dimensional manifold | precision and recall | Mixed |
| Use a continuous dimensionality-reduction map | Dimensionality reduction maps · Information retrieval | precision | Hurt |
| Apply a Lipschitz continuous dimensionality-reduction map | Dimensionality reduction maps · Worst-case retrieval neighborhood | precision: D(n, m)\,\left(\frac{r_U}{R}\right)^{n-m}\,\frac{ r_U^{^{m}} }{p^{m}(r_V/L)} | Hurt |
| Use the Wasserstein lower bound to select the retrieval radius | Dimensionality reduction retrieval · Synthetic samples in a 10-dimensional unit ball | f-score (β=0.3) | Improved |
| Measure retrieval mismatch with L2-Wasserstein distance rather than volume-only precision and recall | Dimensionality reduction retrieval · Information retrieval | distance distortion | Improved |
Closest papers by meaning
- Generalized Dimension Reduction Using Semi-Relaxed Gromov-Wasserstein Distance (AAAI 2025 · similarity 0.86)
- A New Robust Partial p-Wasserstein-Based Metric for Comparing Distributions (ICML 2024 · similarity 0.84)
- Randomized Dimensionality Reduction for Euclidean Maximization and Diversity Measures (ICML 2025 · similarity 0.84)
- Beyond Worst-Case Dimensionality Reduction for Sparse Vectors (ICLR 2025 · similarity 0.84)
- Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding (CVPR 2025 · similarity 0.83)
- Embedding Dimension of Contrastive Learning and $k$-Nearest Neighbors (NeurIPS 2024 · similarity 0.83)
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.
