Research map / Optimization / Nonconvex and smooth optimization
Online sampling from log-concave distributions
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 |
|---|---|---|---|
| Use variance-reduced SGLD with cached gradients and constant batch size | Online sampling · Online sampling | oracle calls per epoch: O_T(T) -> \mathrm{polylog}(T) | Helped |
| Use SGLD without variance reduction | Online sampling · Online sampling | gradient variance | Hurt |
| Reuse cached gradients and correct them with a constant-size batch | Online SAGA-LD · Online sampling | gradient variance | Helped |
| Reset the warm start to the sample at the previous power of 2 when drift exceeds the acceptance radius | Online SAGA-LD · Online sampling | cached-gradient validity | Helped |
Closest papers by meaning
- Chain of Log-Concave Markov Chains (ICLR 2024 · similarity 0.90)
- Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers (ICLR 2024 · similarity 0.89)
- Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel (ICLR 2025 · similarity 0.89)
- Faster Sampling via Stochastic Gradient Proximal Sampler (ICML 2024 · similarity 0.88)
- Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited (ICLR 2024 · 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.