Research map / Optimization / Optimizers
Langevin Monte Carlo: random coordinate descent and variance reduction
Zhiyan Ding, Qin Li
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 |
|---|---|---|---|
| add SVRG or RCAD variance reduction to random-coordinate overdamped LMC (ablation) | RCD-O-LMC · Gaussian, Gaussian mixture and Bayesian linear regression sampling (d up to 1000) | test-function error saturation vs step size h: error saturating at ~h -> ~h^2 | Improved |
| add SVRG or RCAD variance reduction to random-coordinate underdamped LMC (ablation) | RCD-U-LMC · Gaussian, Gaussian mixture and Bayesian linear regression sampling (d up to 1000) | error dependence exponent on step size h: 1 -> ~2.5 | Improved |
Closest papers by meaning
- Variance reduction for Random Coordinate Descent-Langevin Monte Carlo (NeurIPS 2020 · similarity 0.95)
- Langevin Quasi-Monte Carlo (NeurIPS 2023 · similarity 0.93)
- 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 0.88)
- Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling (ICLR 2025 · similarity 0.88)
- Constrained Sampling with Primal-Dual Langevin Monte Carlo (NeurIPS 2024 · similarity 0.88)
- The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models (NeurIPS 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.
