mlsanityData to 14 Oct 2026

A Contour Stochastic Gradient Langevin Dynamics Algorithm for Simulations of Multi-modal Distributions

arXiv 2010.09800 ↗First posted 19 Oct 2020stat.ML cs.LG stat.COcited by 26

Not on the map. Why?

Abstract (arXiv)

We propose an adaptively weighted stochastic gradient Langevin dynamics algorithm (SGLD), so-called contour stochastic gradient Langevin dynamics (CSGLD), for Bayesian learning in big data statistics. The proposed algorithm is essentially a scalable dynamic importance sampler, which automatically flattens the target distribution such that the simulation for a multi-modal distribution can be greatly facilitated. Theoretically, we prove a stability condition and establish the asymptotic convergence of the self-adapting parameter to a it unique fixed-point, regardless of the non-convexity of the original energy function; we also present an error analysis for the weighted averaging estimators. Empirically, the CSGLD algorithm is tested on multiple benchmark datasets including CIFAR10 and CIFAR100. The numerical results indicate its superiority to avoid the local trap problem in training deep neural networks.

Key facts. Cited by 26 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 6; 2024: 5; 2025: 6; 2026: 1.

26 papers.

Sort:

By area:

  1. 2023Provably Convergent Schr"odinger Bridge with Applications to Probabilistic Time Series Imputationcited by 27
  2. 2022Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constantscited by 24
  3. 2024Diffusive Gibbs Samplingcited by 21
  4. 2021On Convergence of Federated Averaging Langevin Dynamicscited by 14
  5. 2021Deep Bayesian inference for seismic imaging with taskscited by 12
  6. 2022Low-Precision Stochastic Gradient Langevin Dynamicscited by 12
  7. 2021Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networkscited by 11
  8. 2022Nonlinear Sufficient Dimension Reduction with a Stochastic Neural Networkcited by 10
  9. 2024Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamicscited by 10
  10. 2022Interacting Contour Stochastic Gradient Langevin Dynamicscited by 9
  11. 2024Gradient-based Discrete Sampling with Automatic Cyclical Schedulingcited by 9
  12. 2023Statistical Inference with Stochastic Gradient Methods under φ-mixing Datacited by 7
14 more
  1. 2024Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamicscited by 7
  2. 2023Non-Log-Concave and Nonsmooth Sampling via Langevin Monte Carlo Algorithmscited by 4
  3. 2024Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusioncited by 4
  4. 2025Morephy-Net: An Evolutionary Multi-objective Optimization for Replica-Exchange-based Physics-informed Neural Operator Learning Networkscited by 3
  5. 2022Refiner: Data Refining against Gradient Leakage Attacks in Federated Learningcited by 2
  6. 2023Gradient-based Wang-Landau Algorithm: A Novel Sampler for Output Distribution of Neural Networks over the Input Spacecited by 2
  7. 2025Opt3DGS: Optimizing 3D Gaussian Splatting with Adaptive Exploration and Curvature-Aware Exploitationcited by 2
  8. 2023Evaluation of human-model prediction difference on the Internet Scale of Datacited by 1
  9. 2025Bayesian Computation in Deep Learningcited by 1
  10. 2025Enhancing Gradient-based Discrete Sampling via Parallel Temperingcited by 1
  11. 2026Slithering Through Gaps: Capturing Discrete Isolated Modes via Logistic Bridgingcited by 1
  12. 2023The surrogate Gibbs-posterior of a corrected stochastic MALA: Towards uncertainty quantification for neural networkscited by 0
  13. 2025Efficient Weighted Sampling via Score-based Generative Modelscited by 0
  14. 2025Flatness-Aware Stochastic Gradient Langevin Dynamicscited by 0