Research map / Probabilistic and scientific modeling / Variational and generative sampling
Parameter elimination in particle Gibbs sampling
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 |
|---|---|---|---|
| Marginalize conjugate parameters from the state update | PGAS · Nonlinear SSM, T=150 | autocorrelation | Helped |
| Increase particle count | PGAS · Nonlinear SSM, T=150 | autocorrelation | Mixed |
| Marginalize conjugate parameters from the state update | PG · Toy nonlinear SSM, T=250 | autocorrelation | Helped |
| Use ancestor sampling | PG · Toy nonlinear SSM, T=250 | autocorrelation | Helped |
| Marginalize conjugate parameters from the state update | PGAS · Toy nonlinear SSM, T=250 | autocorrelation | Helped |
| Use ancestor sampling | PG · Vector-borne disease model, Yap outbreak | autocorrelation | No clear effect |
| Marginalize conjugate parameters from the state update | PG · Vector-borne disease model, Yap outbreak | autocorrelation | Helped |
| Use blocking, with the first block updated by cSMC and the second by mcSMC (ablation) | mPGAS · Nonlinear SSM with diffuse process-noise prior | state update frequency | Helped |
| Marginalize parameters with a diffuse prior without blocking (ablation) | mPGAS · Nonlinear SSM with diffuse process-noise prior | state update frequency | Hurt |
| Marginalize parameters in the state update | PG · Nonlinear SSM, N=500 | runtime: 1231.5s -> 1430.7s | Hurt |
| Marginalize parameters in the state update | PGAS · Nonlinear SSM, N=500 | runtime: 1260.7s -> 1566.1s | Hurt |
Closest papers by meaning
- Poisson-Minibatching for Gibbs Sampling with Convergence Rate Guarantees (NeurIPS 2019 · similarity 0.88)
- Minibatch Gibbs Sampling on Large Graphical Models (ICML 2018 · similarity 0.87)
- Automatically marginalized MCMC in probabilistic programming (ICML 2023 · similarity 0.87)
- Multi-Marginal Couplings for Metropolis--Hastings (NeurIPS 2026 · similarity 0.86)
- Hamiltonian Monte Carlo Inference of Marginalized Linear Mixed-Effects Models (NeurIPS 2024 · similarity 0.85)
- Path-Guided Particle-based Sampling (ICML 2024 · 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.