Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Generalised Bayesian Filtering via Sequential Monte Carlo
Read the paperCheck 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 |
|---|---|---|---|
| Replace the standard likelihood update with a β-divergence update | BPF (FFBS) · London air quality GP regression | NMSE: 0.116 (0.015) -> 0.061(0.003) | Helped |
| Replace the standard likelihood update with a β-divergence update | BPF (FFBS) · London air quality GP regression | EC: 0.650 (0.020) -> 0.760(0.015) | Helped |
| Use β=0.2 instead of β=0.1 (ablation) | β-BPF (FFBS) · London air quality GP regression | NMSE: 0.061(0.003) -> 0.059(0.002) | Helped |
| Use β=0.2 instead of β=0.1 (ablation) | β-BPF (FFBS) · London air quality GP regression | EC: 0.760(0.015) -> 0.803(0.020) | Helped |
| Use β-BPF instead of the Gaussian BPF | BPF · Wiener velocity with contaminated observations | NMSE: around 10× smaller than the BPF | Helped |
| Use β-BPF instead of the Kalman filter | Kalman filter · Wiener velocity with contaminated observations | NMSE: around 100× smaller than the Kalman filter | Helped |
| Use β-BPF or β-APF instead of standard robust filters | BPF and APF · Terrain Aided Navigation | NMSE | Helped |
| Use β-BPF instead of symmetric Student's t likelihoods | t-BPF · Asymmetric Wiener velocity with multiplicative contamination | NMSE | Helped |
Closest papers by meaning
- Outlier-robust Kalman Filtering through Generalised Bayes (ICML 2024 · similarity 0.87)
- Linear approximations to HMM filtering (NeurIPS 2026 · similarity 0.87)
- Inverse Filtering for Hidden Markov Models (NeurIPS 2017 · similarity 0.86)
- State and parameter learning with PARIS particle Gibbs (ICML 2023 · similarity 0.86)
- Learning Robust Statistics for Simulation-based Inference under Model Misspecification (NeurIPS 2023 · similarity 0.85)
- Predictively-Oriented Kalman Filtering (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.