mlsanityData to 7 Oct 2026

Coin Sampling: Gradient-Based Bayesian Inference without Learning Rates

arXiv 2301.11294 ↗First posted 26 Jan 2023stat.ML cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

In recent years, particle-based variational inference (ParVI) methods such as Stein variational gradient descent (SVGD) have grown in popularity as scalable methods for Bayesian inference. Unfortunately, the properties of such methods invariably depend on hyperparameters such as the learning rate, which must be carefully tuned by the practitioner in order to ensure convergence to the target measure at a suitable rate. In this paper, we introduce a suite of new particle-based methods for scalable Bayesian inference based on coin betting, which are entirely learning-rate free. We illustrate the performance of our approach on a range of numerical examples, including several high-dimensional models and datasets, demonstrating comparable performance to other ParVI algorithms with no need to tune a learning rate.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 57 of its 109 references that are in the map. First posted on arXiv 26 Jan 2023.

Builds on

57 of 109 references.

References · 57

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  3. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
  4. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  5. 2019Online Learning: A Modern Introduction Using Convex Optimizationcited by 407
  6. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  7. 2016A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluationcited by 236
  8. 2019Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Sufficescited by 224
  9. 2014Theoretical guarantees for approximate sampling from smooth and log-concave densitiescited by 206
  10. 2018Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantificationcited by 199
  11. 2015Non-asymptotic convergence analysis for the Unadjusted Langevin Algorithmcited by 195
  12. 2018Bayesian Model-Agnostic Meta-Learningcited by 194
38 more
  1. 2017Stein Variational Gradient Descent as Gradient Flowcited by 149
  2. 2015A Complete Recipe for Stochastic Gradient MCMCcited by 146
  3. 2016High-dimensional Bayesian inference via the Unadjusted Langevin Algorithmcited by 144
  4. 2016A Kernel Test of Goodness of Fitcited by 143
  5. 2016Coin Betting and Parameter-Free Online Learningcited by 131
  6. 2018Analysis of Langevin Monte Carlo via convex optimizationcited by 126
  7. 2018Black-Box Reductions for Parameter-free Online Learning in Banach Spacescited by 124
  8. 2018Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problemcited by 123
  9. 2019Maximum Mean Discrepancy Gradient Flowcited by 123
  10. 2017Measuring Sample Quality with Kernelscited by 119
  11. 2017User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradientcited by 116
  12. 2017Convergence of Langevin MCMC in KL-divergencecited by 86
  13. 2019On the geometry of Stein variational gradient descentcited by 82
  14. 2020SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergencecited by 64
  15. 2020A Non-Asymptotic Analysis for Stein Variational Gradient Descentcited by 61
  16. 2022Conditional Simulation Using Diffusion Schr"odinger Bridgescited by 58
  17. 2021Kernel Stein Discrepancy Descentcited by 57
  18. 2018A Stein variational Newton methodcited by 49
  19. 2017Message Passing Stein Variational Gradient Descentcited by 47
  20. 2017Optimal transport for Gaussian mixture modelscited by 45
  21. 2018A Unified Particle-Optimization Framework for Scalable Bayesian Samplingcited by 44
  22. 2018Stein Pointscited by 43
  23. 2018Policy Optimization as Wasserstein Gradient Flowscited by 33
  24. 2020Projected Stein Variational Gradient Descentcited by 33
  25. 2020Blindness of score-based methods to isolated components and mixing proportionscited by 33
  26. 2019Stein Variational Gradient Descent With Matrix-Valued Kernelscited by 32
  27. 2019Parameter-Free Online Convex Optimization with Sub-Exponential Noisecited by 28
  28. 2014Simultaneous Model Selection and Optimization through Parameter-free Stochastic Learningcited by 27
  29. 2017Learning to Draw Samples with Amortized Stein Variational Gradient Descentcited by 26
  30. 2017Riemannian Stein Variational Gradient Descent for Bayesian Inferencecited by 24
  31. 2020Sliced Kernelized Stein Discrepancycited by 23
  32. 2022A Finite-Particle Convergence Rate for Stein Variational Gradient Descentcited by 22
  33. 2016Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learningcited by 21
  34. 2021A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1cited by 21
  35. 2020Better Parameter-free Stochastic Optimization with ODE Updates for Coin-Bettingcited by 19
  36. 2022Sampling with Mollified Interaction Energy Descentcited by 17
  37. 2019Understanding MCMC Dynamics as Flows on the Wasserstein Spacecited by 14
  38. 2018Stein Variational Gradient Descent Without Gradientcited by 12

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 3.

8 papers.

  1. 2023Interacting Particle Langevin Algorithm for Maximum Marginal Likelihood Estimationcited by 17
  2. 2023Entropy-based Training Methods for Scalable Neural Implicit Samplercited by 13
  3. 2023Momentum Particle Maximum Likelihoodcited by 12
  4. 2023Tuning-Free Maximum Likelihood Training of Latent Variable Models via Coin Bettingcited by 11
  5. 2024The Price of Adaptivity in Stochastic Convex Optimizationcited by 11
  6. 2023Learning Rate Free Sampling in Constrained Domainscited by 3
  7. 2024Learning-Rate-Free Stochastic Optimization over Riemannian Manifoldscited by 1
  8. 2024Denoising Fisher Training For Neural Implicit Samplerscited by 0