Research map / Learning theory and algorithms / Prediction and decision losses
No Pressure! Addressing the Problem of Local Minima in Manifold Learning Algorithms
Max Vladymyrov
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 |
|---|---|---|---|
| Add pressured-points optimization from random initialization | Elastic Embedding with Spectral Direction · COIL-20 (10 objects) | objective function value: 3.84 ± 0.18 -> 3.6 ± 0.14 | Improved |
| Add pressured-points optimization after SD convergence | Elastic Embedding with Spectral Direction · COIL-20 (10 objects) | objective function value: 3.84 ± 0.18 -> 3.61 ± 0.19 | Improved |
| Add pressured-points optimization from random initialization | SNE with Spectral Direction · COIL-20 (10 objects) | objective function value: 11.07 ± 0.03 -> 11.03 ± 0.02 | Improved |
| Add pressured-points optimization after SD convergence | SNE with Spectral Direction · COIL-20 (10 objects) | objective function value: 11.07 ± 0.03 -> 11.05 ± 0.03 | Improved |
| Add pressured-points optimization after SD | Elastic Embedding · COIL-20 | objective function value: 3.68 -> 3.3 | Improved |
| Apply pressured-points optimization to the long-tailed kernels | t-SNE and UMAP · Experiments described in the paper | objective function value decrease | No clear effect |
| Use pressured-points optimization | Elastic Embedding with FMM approximation (p=5) · MNIST | objective function value | Improved |
| Use pressured-points optimization after SD | Elastic Embedding · word2vec vectors from Google News (5,000 words) | objective function value | Improved |
Closest papers by meaning
- Manifold Coordinates with Physical Meaning (JMLR 2022 · similarity 0.89)
- When Locally Linear Embedding Hits Boundary (JMLR 2023 · similarity 0.88)
- DLME: Deep Local-Flatness Manifold Embedding (ECCV 2022 · similarity 0.87)
- A Study of the Classification of Low-Dimensional Data with Supervised Manifold Learning (JMLR 2018 · similarity 0.87)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.86)
- Geometric Analysis of Nonlinear Manifold Clustering (NeurIPS 2024 · 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.
