Research map / Probabilistic and scientific modeling / Variational and generative sampling
Nonparametric Involutive Markov Chain 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 |
|---|---|---|---|
| Add persistence with α=0.5 (ablation) | NP-DHMC, L=5 · Geometric distribution | TVD from ground truth: 0.0524 ± 0.0069 -> 0.0464 ± 0.0074 | Helped |
| Add persistence with α=0.1 (ablation) | NP-DHMC, L=5 · Geometric distribution | TVD from ground truth: 0.0524 ± 0.0069 -> 0.0461 ± 0.0083 | Helped |
| Add persistence with α=0.5 (ablation) | NP-DHMC, L=2 · Geometric distribution | TVD from ground truth: 0.0768 ± 0.0181 -> 0.0570 ± 0.0115 | Helped |
| Add persistence with α=0.1 (ablation) | NP-DHMC, L=2 · Geometric distribution | TVD from ground truth: 0.0768 ± 0.0181 -> 0.0534 ± 0.0058 | Helped |
| Use persistence (ablation) | NP-DHMC · Random walk | ESS | Helped |
| Add look-ahead with K=1 or K=2 on top of persistence (ablation) | NP-DHMC with persistence · Random walk | ESS | Helped |
| Add look-ahead with K=1 or K=2 (ablation) | NP-DHMC · Unbounded Gaussian mixture model | LPPD | Helped |
| Add persistence with α=0.5 (ablation) | NP-DHMC · Unbounded Gaussian mixture model | LPPD | Helped |
| Add persistence with α=0.5 (ablation) | NP-DHMC · Dirichlet process mixture model | LPPD | Mixed |
| Add look-ahead with K=1 or K=2 (ablation) | NP-DHMC · Dirichlet process mixture model | LPPD | Helped |
Closest papers by meaning
- Nonparametric Hamiltonian Monte Carlo (ICML 2021 · similarity 0.93)
- Involutive MCMC: a Unifying Framework (ICML 2020 · similarity 0.91)
- Automatically marginalized MCMC in probabilistic programming (ICML 2023 · similarity 0.90)
- Measuring the reliability of MCMC inference with bidirectional Monte Carlo (NeurIPS 2016 · similarity 0.89)
- AutoStep: Locally adaptive involutive MCMC (ICML 2025 · similarity 0.87)
- Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows (NeurIPS 2024 · similarity 0.84)
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.