Research map / Optimization / Nonconvex and smooth optimization
Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates
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 stochastic proximal operators for nonsmooth graph total-variation terms instead of stochastic subgradients | SPLA versus SSLA · Graph Trend Filtering: Facebook, YouTube, Amazon, and DBLP graphs | Numerical stability | Helped |
| Use stochastic updates instead of a full proximity operator | SPLA and SSLA versus ProxLA · Graph Trend Filtering, Facebook graph | Update frequency: about one hundred times more frequently | Helped |
| Use stochastic proximal operators instead of stochastic subgradients | SPLA versus SSLA · Graph Trend Filtering, large graphs | Functional value over CPU time | Helped |
| Use stochastic proximity steps rather than stochastic subgradient steps | SPLA versus SSLA · Laplace sampling toy model | Sampling precision | Helped |
Closest papers by meaning
- Faster Sampling via Stochastic Gradient Proximal Sampler (ICML 2024 · similarity 0.93)
- Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm (NeurIPS 2020 · similarity 0.93)
- From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling (NeurIPS 2025 · similarity 0.90)
- Langevin Monte Carlo Beyond Lipschitz Gradient Continuity (AAAI 2025 · similarity 0.90)
- Fast Non-Log-Concave Sampling under Nonconvex Equality and Inequality Constraints with Landing (NeurIPS 2025 · similarity 0.88)
- Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited (ICLR 2024 · similarity 0.88)
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.