Research map / Optimization / Nonconvex and smooth optimization
Optimal Underdamped Langevin MCMC Method
Zhengmian Hu, Feihu Huang, Heng Huang
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 SAGA variance reduction in ALUM instead of full gradient | ALUM · Gaussian model and australian logistic regression | trajectory error vs gradient evaluations | Improved |
| use variance-reduced gradients instead of full gradient | ALUM, LPM, RMM · Gaussian model and australian logistic regression | trajectory error vs gradient evaluations | Improved |
| use ALUM instead of RMM with full gradient | ULD discretization · Gaussian model | trajectory error vs gradient evaluations | Improved |
| use ALUM or RMM instead of LPM with full gradient | ULD discretization · Gaussian model | trajectory error vs gradient evaluations | Improved |
| use plain stochastic gradient in ALUM vs LPM | ULD discretization · Gaussian model | trajectory error | No clear effect |
Closest papers by meaning
- Underdamped Langevin MCMC with third order convergence (JMLR 2026 · similarity 0.93)
- Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence (ICML 2026 · similarity 0.89)
- Bounding the Error of Discretized Langevin Algorithms for Non-Strongly Log-Concave Targets (JMLR 2022 · similarity 0.89)
- Mean-field Underdamped Langevin Dynamics and its Spacetime Discretization (ICML 2024 · similarity 0.88)
- From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling (NeurIPS 2025 · similarity 0.87)
- Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited (ICLR 2024 · 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.
