Research map / Learning theory and algorithms / Optimal transport
Riemannian Metric Learning via Optimal Transport
Christopher Scarvelis, Justin Solomon
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 learned Riemannian metric for scRNA trajectory inference instead of the non-regularized baseline | Trajectory inference model · scRNA trajectory inference, k ≥ 10 | mean EMD: 19.7% mean reduction in EMD | Improved |
| Use the learned Riemannian metric instead of Euclidean geodesics | Snow goose trajectory inference · Snow goose trajectories | mean DTW distance: 26.9% reduction in mean DTW distance | Improved |
| Use the Euclidean metric regularizer instead of no regularizer | scRNA trajectory inference · scRNA trajectory inference | mean EMD | Hurt |
| Increase regularization coefficient λ to 10^5 (ablation) | Learned Riemannian metric · Circular synthetic metric recovery | eigenspace alignment: alignment score falls to 0.857 | Hurt |
| Vary regularization coefficient λ across the tested values, excluding the largest value (ablation) | Learned Riemannian metric · Circular synthetic metric recovery | eigenspace alignment | No clear effect |
| Remove the optimal transport term (ablation) | Learned Riemannian metric · Circular synthetic metric recovery | data-informed metric recovery | Hurt |
Closest papers by meaning
- Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models (NeurIPS 2025 · similarity 0.87)
- Learning Distances from Data with Normalizing Flows and Score Matching (ICML 2025 · similarity 0.86)
- RMLR: Extending Multinomial Logistic Regression into General Geometries (NeurIPS 2024 · similarity 0.86)
- Task-Induced Riemannian Metrics for Vision Transformer Feature Spaces (NeurIPS 2026 · similarity 0.86)
- Riemannian Geometric-based Meta Learning (AAAI 2025 · similarity 0.85)
- Geometry-Aware Similarity Metrics for Neural Representations on Riemannian and Statistical Manifolds (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.
