Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Bayesian Variance Change Point Detection With Credible Sets
Lorenzo Cappello, Oscar Hernán Madrid Padilla
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 PRISCA instead of MCP | variance change point detection · Gaussian variance change simulation (T=1000) | Hausdorff distance: 360.61 -> 200.83 | Improved |
| use PRISCA instead of MCP (runtime) | Bayesian change point detection · Gaussian variance change simulation (T=1000) | time (s): 1830.2 -> 1.69 | Improved |
| use PRISCA instead of PELT | variance change point detection · Gaussian variance change simulation (T=1000) | Hausdorff distance: 263.76 -> 200.83 | Improved |
| use PRISCA instead of BINSEG | variance change point detection · Gaussian variance change simulation (T=1000) | bias K-K_hat: 3.91 -> 2.55 | Improved |
| give oracle knowledge of K (ora-PRISCA) (ablation) | PRISCA · Gaussian variance change simulation (T=1000) | Hausdorff distance: 200.83 -> 181.32 | Improved |
| give oracle knowledge of K (ora-PRISCA) (ablation) | PRISCA · Gaussian variance change simulation (T=1000) | bias K-K_hat: 2.55 -> 2.55 | No clear effect |
| choose L automatically (auto-PRISCA) instead of L=T/30 (ablation) | PRISCA · Gaussian variance change simulation (T=1000) | Hausdorff distance: 200.83 -> 186.07 | Mixed |
| choose L automatically (auto-PRISCA) instead of L=T/30 (ablation) | PRISCA · Gaussian variance change simulation (T=1000) | time (s): 1.69 -> 2.82 | Hurt |
| knowledge of K (ora-PRISCA) (ablation) | PRISCA · Gaussian variance change simulation (T=200) | conditional coverage: 0.82 -> 0.83 | Improved |
| use PRISCA credible sets instead of MCP | variance change point detection · Gaussian variance change simulation (T=1000) | credible set length: 93.46 -> 23.91 | Improved |
| use PRISCA (VB) instead of MCP for coverage | credible sets · Gaussian variance change simulation (T=1000) | conditional coverage: 0.99 -> 0.86 | Hurt |
| vary prior a0 (ablation) | PRISCA · Gaussian variance change simulation | accuracy | No clear effect |
Closest papers by meaning
- Bayesian Model Selection for Change Point Detection and Clustering (ICML 2018 · similarity 0.90)
- Bayesian online change point detection with Hilbert space approximate Student-t process (ICML 2023 · similarity 0.87)
- Robust and Scalable Bayesian Online Changepoint Detection (ICML 2023 · similarity 0.86)
- Optimistic Search: Change Point Estimation for Large-scale Data via Adaptive Logarithmic Queries (JMLR 2024 · similarity 0.86)
- Conjugate Bayesian Two-step Change Point Detection for Hawkes Process (NeurIPS 2024 · similarity 0.83)
- Reducing sequential change detection to sequential estimation (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.
