Research map / Learning theory and algorithms / Matrix and tensor methods
Trajectory Seriation via Spectral Tangent Alignment and Global Embedding
Zhixin Zhou, Navin Souda, Arash A. Amini
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 orientation-alignment step before the final embedding (ablation) | STAGE · Synthetic Fourier curves | Kendall tau | Improved |
| replace 1D t-SNE with STAGE | 1D t-SNE · Synthetic Fourier curves (n=2000, d=200, sigma=2) | Kendall tau: 77.47 -> 81.18 | Improved |
| replace 1D t-SNE with STAGE | 1D t-SNE · Synthetic Fourier curves (n=2000, d=50, sigma=0.5) | Kendall tau: 90.51 -> 90.91 | Improved |
| replace Recanati with STAGE | Recanati · Synthetic Fourier curves (n=2000, d=50, sigma=2) | Kendall tau: 64.39 -> 64.04 | No clear effect |
| replace Fiedler vector with STAGE | Fiedler Vector · Synthetic Fourier curves (n=2000, d=50, sigma=2) | Kendall tau: 33.22 -> 64.04 | Improved |
| replace 1D UMAP with STAGE | 1D UMAP · Synthetic Fourier curves (n=2000, d=200, sigma=2) | Kendall tau: 70.17 -> 81.18 | Improved |
| raise noise sigma from 0.5 to 2 | STAGE · Synthetic Fourier curves (n=2000, d=50) | Kendall tau: 90.91 -> 64.04 | Hurt |
| raise ambient dimension from 50 to 200 | STAGE · Synthetic Fourier curves (n=2000, sigma=2) | Kendall tau: 64.04 -> 81.18 | Improved |
| replace 1D t-SNE with STAGE | 1D t-SNE · Saelens embryo scRNA-seq | Kendall tau: 0.808 -> 0.786 | Hurt |
| replace 1D t-SNE with STAGE | 1D t-SNE · Packer seam cells scRNA-seq | Kendall tau: 0.889 -> 0.926 | Improved |
| replace 1D t-SNE with STAGE | 1D t-SNE · Packer hypodermis scRNA-seq | Kendall tau: 0.801 -> 0.822 | Improved |
| vary neighborhood size k (ablation) | STAGE · Synthetic Fourier curves | Kendall tau | No clear effect |
Closest papers by meaning
- Generalized Laplacian in Spectral Seriation on Manifold Data (NeurIPS 2026 · similarity 0.86)
- Fast Alignment of Embeddings: Computational Guarantees for Anisotropic Procrustes-Wasserstein (NeurIPS 2026 · similarity 0.86)
- Metric Flow Matching for Smooth Interpolations on the Data Manifold (NeurIPS 2024 · similarity 0.84)
- Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem (NeurIPS 2024 · similarity 0.84)
- GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories (NeurIPS 2026 · similarity 0.84)
- Euclidean Embedding of Data Using Local Distances (NeurIPS 2026 · similarity 0.84)
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.
