Research map / Optimization / Optimizers
Decentralized Langevin Dynamics for Bayesian Learning
Anjaly Parayil, He Bai, Jemin George, Prudhvi Gurram
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 D-ULA with 10 agents instead of centralized ULA | Bayesian logistic regression · a9a | test accuracy (%): 83.89 -> 84.5637 | Improved |
| Use D-ULA instead of centralized ULA | Bayesian logistic regression · a9a | convergence speed | Improved |
| Increase number of agents from 1 to 10 (ablation) | D-ULA · Gaussian mixture | Sinkhorn distance: 0.259 -> 0.244 | Improved |
| Use D-ULA (5 agents) instead of SGD | LeNet-5 · MNIST | test accuracy (%): 98.15 -> 98.52 | Improved |
| Use Langevin sampling (C-ULA/D-ULA) instead of SGD point estimate | LeNet-5 · SVHN OOD detection | mean predicted probability (lower better on OOD): 0.849 -> 0.651 | Improved |
| Use D-ULA instead of C-ULA for OOD detection | LeNet-5 · SVHN OOD detection | mean predicted probability: 0.849 -> 0.604 | Improved |
Closest papers by meaning
- Decentralized Stochastic Gradient Langevin Dynamics and Hamiltonian Monte Carlo (JMLR 2021 · similarity 0.89)
- A Dynamical System View of Langevin-Based Non-Convex Sampling (NeurIPS 2023 · similarity 0.88)
- Aggregated Gradient Langevin Dynamics (AAAI 2020 · similarity 0.87)
- DG-LMC: A Turn-key and Scalable Synchronous Distributed MCMC Algorithm via Langevin Monte Carlo within Gibbs (ICML 2021 · similarity 0.87)
- A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions (NeurIPS 2020 · similarity 0.87)
- Enhancing Parallelism in Decentralized Stochastic Convex Optimization (ICML 2025 · similarity 0.86)
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.
