Research map / Probabilistic and scientific modeling / Variational and generative sampling
Pseudo-Marginal Hamiltonian Monte Carlo
Johan Alenlöv, Arnoud Doucet, Fredrik Lindsten
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 |
|---|---|---|---|
| increase the number of importance samples N in PM-HMC (ablation) | PM-HMC · Gaussian model | max position error vs ideal HMC: slope of the linear fit is -0.509 | Improved |
| increase N in PM-HMC (ablation) | PM-HMC · Gaussian model | acceptance probability: For N = 1 the mean is 0.16 | Improved |
| use PM-HMC instead of standard HMC on the joint space | standard HMC (non-centered) · Diffraction model | exploration of posterior (qualitative scatter) | Improved |
| use PM-HMC instead of pseudo-marginal slice sampling | pseudo-marginal slice sampling · Diffraction model | performance normalized by computational cost | No clear effect |
| use PM-HMC instead of pseudo-marginal slice sampling and Particle Gibbs | GLMM sampler (N=128) · Gaussian-mixture logistic GLMM (T=500) | mixing of mu1, mu2 traces: cost per iteration about 3.5 times higher than slice sampling | Improved |
Closest papers by meaning
- Pseudo-Extended Markov chain Monte Carlo (NeurIPS 2019 · similarity 0.91)
- Mixed Hamiltonian Monte Carlo for Mixed Discrete and Continuous Variables (NeurIPS 2020 · similarity 0.90)
- Multi-fidelity Monte Carlo: a pseudo-marginal approach (NeurIPS 2022 · similarity 0.90)
- Metropolis Adjusted Microcanonical Hamiltonian Monte Carlo (NeurIPS 2025 · similarity 0.88)
- Parallelizing MCMC Across the Sequence Length (NeurIPS 2025 · similarity 0.86)
- Hamiltonian Monte Carlo Inference of Marginalized Linear Mixed-Effects Models (NeurIPS 2024 · similarity 0.86)
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.
