Research map / Optimization / Nonconvex and smooth optimization
Stochastic Variance-Reduced Hamilton Monte Carlo Methods
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 |
|---|---|---|---|
| Variance-reduced semi-stochastic gradient in HMC (SVR-HMC) vs. SG-HMC | HMC sampler · Bayesian logistic regression, 4 datasets | test error after 10 data passes | Mixed |
| Variance reduction (VR-SGLD) vs. SGLD | Langevin sampler · Bayesian logistic regression | test error after 10 data passes | Mixed |
| Synthetic Gaussian experiments: SVR-HMC vs SG-HMC and HMC in 2-Wasserstein | HMC sampler · synthetic Gaussian, d in {10,50}, n in {50..5000} | 2-Wasserstein convergence vs data passes | Mixed |
| Variance reduction on Bayesian linear regression | SVR-HMC · geographical, noise, parkinson, toms | test mean square error vs data passes | Helped |
Closest papers by meaning
- Stochastic Gradient Hamiltonian Monte Carlo Methods with Recursive Variance Reduction (NeurIPS 2019 · similarity 0.95)
- On the Convergence of Hamiltonian Monte Carlo with Stochastic Gradients (ICML 2021 · similarity 0.94)
- A Hybrid Stochastic Gradient Hamiltonian Monte Carlo Method (AAAI 2021 · similarity 0.92)
- Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion (NeurIPS 2024 · similarity 0.88)
- Metropolis Adjusted Microcanonical Hamiltonian Monte Carlo (NeurIPS 2025 · similarity 0.87)
- Non-asymptotic Error Bounds in $\mathcal{W}_2$-Distance with Sqrt(d) Dimension Dependence and First Order Convergence for Langevin Monte Carlo beyond Log-Concavity (ICML 2025 · similarity 0.87)
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.