Research map / Point clouds / Point cloud classification
A Framework for Fast and Stable Representations of Multiparameter Persistent Homology Decompositions
David Loiseaux, Mathieu Carrière, Andrew Blumberg
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 proposed stable decomposition representation instead of the strongest listed baseline | UCR classification · GP | accuracy: 94.0 -> 96.3 | Improved |
| Use the proposed stable decomposition representation instead of the strongest listed baseline | UCR classification · IPD | accuracy: 95.5 -> 81.2 | Hurt |
| Use the proposed stable decomposition representation instead of the strongest listed baseline | UCR classification · GPMVF | accuracy: 99.7 -> 95.3 | Hurt |
| Use the proposed stable decomposition representation instead of the strongest listed baseline | UCR classification · GPAS | accuracy: 96.5 -> 88.0 | Hurt |
| Use the proposed stable decomposition representation instead of the strongest listed baseline | UCR classification · DPOAG | accuracy: 77.0 -> 71.9 | Hurt |
| Use the proposed stable decomposition representation instead of the strongest listed baseline | UCR classification · PPOAG | accuracy: 82.0 -> 81.9 | No clear effect |
| Use the proposed stable decomposition representation instead of Ripley, P, or MPL | Immunohistochemistry classification · Immunohistochemistry | accuracy: 67.2 ± 2.3 -> 91.4 ± 1.6; 60.7 ± 4.2 -> 91.4 ± 1.6; 65.3 ± 3.0 -> 91.4 ± 1.6 | Improved |
| Use the proposed representation rather than MPI (50) or MPL (50) | Annulus and immunohistochemistry representation computation · Annulus and Immunohistochemistry | runtime: 250ms± 2ms vs 6.43s± 25ms; 250ms± 2ms vs 17s± 39ms; 275 ms ± 9.8ms vs 5.67s ± 23.3ms; 275 ms ± 9.8ms vs 15.6s ± 14ms | Improved |
| Use stable representations of candidate decompositions rather than MPI | Noisy annulus convergence experiment · Noisy annulus | convergence | Improved |
| Choose stable representation parameters rather than the MPI representation | Multiparameter persistence representation · Perturbations of decompositions | stability | Improved |
Closest papers by meaning
- On the Effectiveness of Persistent Homology (NeurIPS 2022 · similarity 0.93)
- Differentiability and Optimization of Multiparameter Persistent Homology (ICML 2024 · similarity 0.91)
- Point-Level Topological Representation Learning on Point Clouds (ICML 2025 · similarity 0.91)
- The Flood Complex: Large-Scale Persistent Homology on Millions of Points (NeurIPS 2025 · similarity 0.90)
- Graphcode: Learning from multiparameter persistent homology using graph neural networks (NeurIPS 2024 · similarity 0.89)
- Persistent Homology for High-dimensional Data Based on Spectral Methods (NeurIPS 2024 · similarity 0.89)
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.
