mlsanityData to 7 Oct 2026

GAD-PVI: A General Accelerated Dynamic-Weight Particle-Based Variational Inference Framework

arXiv 2312.16429 ↗First posted 27 Dec 2023cs.LG cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Particle-based Variational Inference (ParVI) methods approximate the target distribution by iteratively evolving finite weighted particle systems. Recent advances of ParVI methods reveal the benefits of accelerated position update strategies and dynamic weight adjustment approaches. In this paper, we propose the first ParVI framework that possesses both accelerated position update and dynamical weight adjustment simultaneously, named the General Accelerated Dynamic-Weight Particle-based Variational Inference (GAD-PVI) framework. Generally, GAD-PVI simulates the semi-Hamiltonian gradient flow on a novel Information-Fisher-Rao space, which yields an additional decrease on the local functional dissipation. GAD-PVI is compatible with different dissimilarity functionals and associated smoothing approaches under three information metrics. Experiments on both synthetic and real-world data demonstrate the faster convergence and reduced approximation error of GAD-PVI methods over the state-of-the-art.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 35 of its 81 references that are in the map. First posted on arXiv 27 Dec 2023.

Builds on

35 of 81 references.

References · 35

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  3. 2016Variational Inference: A Review for Statisticianscited by 1,466
  4. 2018Computational Optimal Transportcited by 765
  5. 2017Reinforcement Learning with Deep Energy-Based Policiescited by 659
  6. 2016Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithmcited by 498
  7. 2014Stochastic Gradient Hamiltonian Monte Carlocited by 341
  8. 2013Black Box Variational Inferencecited by 317
  9. 2016A Kernelized Stein Discrepancy for Goodness-of-fit Tests and Model Evaluationcited by 236
  10. 2013Fast Computation of Wasserstein Barycenterscited by 216
  11. 2017A Conceptual Introduction to Hamiltonian Monte Carlocited by 207
  12. 2017Stein Variational Gradient Descent as Gradient Flowcited by 149
23 more
  1. 2019Maximum Mean Discrepancy Gradient Flowcited by 123
  2. 2016A Variational Perspective on Accelerated Methods in Optimizationcited by 108
  3. 2018Deep Bayesian Active Learning for Natural Language Processing: Results of a Large-Scale Empirical Studycited by 90
  4. 2020A Non-Asymptotic Analysis for Stein Variational Gradient Descentcited by 61
  5. 2021Kernel Stein Discrepancy Descentcited by 57
  6. 2020What Can Be Transferred: Unsupervised Domain Adaptation for Endoscopic Lesions Segmentationcited by 50
  7. 2019Accelerating Langevin Sampling with Birth-deathcited by 45
  8. 2018A Unified Particle-Optimization Framework for Scalable Bayesian Samplingcited by 44
  9. 2018Stein Pointscited by 43
  10. 2017Stein Variational Policy Gradientcited by 42
  11. 2019Accelerated Information Gradient flowcited by 38
  12. 2023Optimal Transport for Treatment Effect Estimationcited by 32
  13. 2019Global convergence of neuron birth-death dynamicscited by 22
  14. 2016Learning to Draw Samples: With Application to Amortized MLE for Generative Adversarial Learningcited by 21
  15. 2018Stochastic Particle-Optimization Sampling and the Non-Asymptotic Convergence Theorycited by 20
  16. 2022Sampling with Mollified Interaction Energy Descentcited by 17
  17. 2019Accelerated Flow for Probability Distributionscited by 15
  18. 2021Stein Variational Gradient Descent: many-particle and long-time asymptoticscited by 15
  19. 2021Geometric variational inferencecited by 12
  20. 2020Unbalanced Sobolev Descentcited by 11
  21. 2020Sinkhorn Barycenter via Functional Gradient Descentcited by 9
  22. 2021DPVI: A Dynamic-Weight Particle-Based Variational Inference Frameworkcited by 7
  23. 2021De-randomizing MCMC dynamics with the diffusion Stein operatorcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 4.

9 papers.

  1. 2024BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Modelscited by 29
  2. 2026Mass Concept Erasure in Diffusion Models with Concept Hierarchycited by 14
  3. 2024DriveDiTFit: Fine-tuning Diffusion Transformers for Autonomous Drivingcited by 11
  4. 2025Efficiently Access Diffusion Fisher: Within the Outer Product Span Spacecited by 5
  5. 2025Unleashing High-Quality Image Generation in Diffusion Sampling Using Second-Order Levenberg-Marquardt-Langevincited by 5
  6. 2026FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearningcited by 5
  7. 2024Rethinking the Diffusion Models for Numerical Tabular Data Imputation from the Perspective of Wasserstein Gradient Flowcited by 3
  8. 2026Rethinking the Flow-Based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspectivecited by 0
  9. 2026Slack More, Predict Better: Proximal Relaxation for Probabilistic Latent Variable Model-based Soft Sensorscited by 0