Research map / Probabilistic and scientific modeling / Variational and generative sampling
Fast mixing of Metropolized Hamiltonian Monte Carlo: Benefits of multi-step gradients
Yuansi Chen, Raaz Dwivedi, Martin J. Wainwright, Bin Yu
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 Metropolized HMC with theory-chosen step size and leapfrog steps instead of MALA | Metropolized HMC · Gaussian, kappa=4 | log-log slope of evaluations vs dimension: 0.93 -> 0.80 | Improved |
| use aggressive step size and more leapfrog steps (HMCagg) instead of standard HMC parameters (ablation) | HMC · Gaussian, kappa=4 | log-log slope of evaluations vs dimension: 0.80 -> 0.58 | Improved |
| use HMC instead of MRW | Metropolized HMC · Gaussian, kappa=d^(2/3) | log-log slope of evaluations vs dimension: 2.25 -> 1.60 | Improved |
| use aggressive parameters (HMCagg) instead of standard HMC (ablation) | HMC · Gaussian, kappa=d^(2/3) | log-log slope of evaluations vs dimension: 1.60 -> 1.34 | Improved |
Closest papers by meaning
- Hamiltonian Monte Carlo for efficient Gaussian sampling: long and random steps (JMLR 2024 · similarity 0.93)
- Entropy-based adaptive Hamiltonian Monte Carlo (NeurIPS 2021 · similarity 0.93)
- Hamiltonian Monte Carlo with Energy Conserving Subsampling (JMLR 2019 · similarity 0.91)
- On the Convergence of Hamiltonian Monte Carlo with Stochastic Gradients (ICML 2021 · similarity 0.91)
- A Gradient Based Strategy for Hamiltonian Monte Carlo Hyperparameter Optimization (ICML 2021 · similarity 0.91)
- Metropolis Adjusted Microcanonical Hamiltonian Monte Carlo (NeurIPS 2025 · similarity 0.91)
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.
