Research map / Optimization / Nonconvex and smooth optimization
Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm
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 PSGLA instead of MYULA (no Moreau-Yosida smoothing parameter) for sampling from Wishart posterior | Langevin sampling with nonsmooth G taking infinite values · Wishart posterior, d=1 histograms | closeness of sample histogram to target | Helped |
| use PSGLA instead of MYULA | Langevin sampling, Wishart posterior · Wishart posterior | feasibility of iterates (in support) | Helped |
| use PSGLA instead of MYULA with best lambda | mean a posteriori estimation, d=10 and d=100 · Wishart posterior, Frobenius error of ergodic mean | Frobenius distance to true mean | No clear effect |
| use larger step size with PSGLA versus MYULA | Langevin algorithm · Wishart posterior | numerical stability | Helped |
Closest papers by meaning
- From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling (NeurIPS 2025 · similarity 0.91)
- Faster Sampling via Stochastic Gradient Proximal Sampler (ICML 2024 · similarity 0.90)
- Constrained Sampling with Primal-Dual Langevin Monte Carlo (NeurIPS 2024 · similarity 0.90)
- Generalization of noisy SGD in unbounded non-convex settings (ICML 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)
- 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.