Research map / Learning theory and algorithms / Matrix and tensor methods
An Efficient Exact-PGA Algorithm for Constant Curvature Manifolds
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 CCM-EPGA instead of PGA | PGA on Data_1 · Data_1 | average projection error: 0.174 -> 1.13e-04 | Helped |
| Use CCM-EPGA instead of exact PGA | exact PGA on Data_1 · Data_1 | time (s): 14853 -> 0.70 | Helped |
| Use CCM-EPGA instead of PGA | PGA on Data_2 · Data_2 | average projection error: 0.59 -> 5.87e-02 | Helped |
| Use CCM-EPGA instead of PGA | PGA on Data_3 · Data_3 | average projection error: 0.55 -> 2.33e-03 | Helped |
| Use CCM-EPGA instead of exact PGA | exact PGA on Data_3 · Data_3 | time (s): 16.87 -> 0.19 | Helped |
| Use CCM-EPGA instead of PGA | PGA on Data_4 · Data_4 | average projection error: 0.37 -> 0.27 | Helped |
| Use CCM-EPGA instead of PGA | PGA on Data_4 · Data_4 | time (s): 0.14 -> 0.33 | Hurt |
| Use CCM-EPGA instead of PGA | PGA on GatorBait-100 · GatorBait-100 | average projection error: 9.68e-02 -> 2.83e-10 | Helped |
| Use CCM-EPGA instead of PGA | PGA on GatorBait-100 · GatorBait-100 | time (s): 0.28 -> 0.40 | Hurt |
| Use CCM-EPGA instead of PGA | PGA on Brodatz · Brodatz | average projection error: 0.14 -> 7.73e-03 | Helped |
| Use CCM-EPGA instead of exact PGA | exact PGA on Brodatz · Brodatz | time (s): 732 -> 0.09 | Helped |
Closest papers by meaning
- Riemannian coordinate descent algorithms on matrix manifolds (ICML 2024 · similarity 0.85)
- Fun with Flags: Robust Principal Directions via Flag Manifolds (CVPR 2024 · similarity 0.85)
- Preconditioned Riemannian Gradient Descent Algorithm for Low-Multilinear-Rank Tensor Completion (ICML 2025 · similarity 0.84)
- Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models (NeurIPS 2025 · similarity 0.84)
- Flow Matching on General Geometries (ICLR 2024 · similarity 0.83)
- Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point (ICML 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.