Research map / Learning theory and algorithms / Matrix and tensor methods
How can classical multidimensional scaling go wrong?
Rishi Sonthalia, Greg Vanbuskirk, Benjamin Raichel, Anna Gilbert
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 |
|---|---|---|---|
| increase embedding dimension | cMDS · perturbed Euclidean metrics (heart) | relative SSTRESS vs perturbed input | Hurt |
| increase embedding dimension | cMDS · perturbed Euclidean metrics (heart) | relative squared error to original metric (denoising) | Hurt |
| increase embedding dimension | cMDS · Portugal graph and Isomap on heart | relative squared error | Hurt |
| replace cMDS with Lower + cMDS | cMDS · Celegans, Portugal, heart (perturbed, Isomap) | relative SSTRESS | Improved |
| replace cMDS with Lower + cMDS | cMDS embeddings + 3-layer NN · MNIST, Fashion MNIST, CIFAR10 (perturbed, kNN-graph, missing pixels) | classification accuracy as dimension grows | Improved |
| increase embedding dimension for classification | cMDS embeddings + 3-layer NN · MNIST, Fashion MNIST, CIFAR10 non-Euclidean metrics | classification accuracy | Hurt |
| use lower bound solution in place of true SSTRESS minimizer | Lower bound algorithm · relative squared error | tracking of true SSTRESS solution | Improved |
| use Lower + cMDS vs true SSTRESS solution for compute | Lower + cMDS · Portugal and classification experiments | running time | Improved |
Closest papers by meaning
- Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms (NeurIPS 2024 · similarity 0.86)
- Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding (CVPR 2025 · similarity 0.84)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.84)
- MetricEmbedding: Accelerate Metric Nearness by Tropical Inner Product (ICML 2025 · similarity 0.84)
- Generalized Dimension Reduction Using Semi-Relaxed Gromov-Wasserstein Distance (AAAI 2025 · similarity 0.84)
- Johnson-Lindenstrauss Lemma Beyond Euclidean Geometry (NeurIPS 2025 · 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.
