mlsanityData to 7 Oct 2026

Variational Inference using Implicit Distributions

arXiv 1702.08235 ↗First posted 27 Feb 2017stat.ML cs.LGcited by 39

Not on the map. Why?

Abstract (arXiv)

Generative adversarial networks (GANs) have given us a great tool to fit implicit generative models to data. Implicit distributions are ones we can sample from easily, and take derivatives of samples with respect to model parameters. These models are highly expressive and we argue they can prove just as useful for variational inference (VI) as they are for generative modelling. Several papers have proposed GAN-like algorithms for inference, however, connections to the theory of VI are not always well understood. This paper provides a unifying review of existing algorithms establishing connections between variational autoencoders, adversarially learned inference, operator VI, GAN-based image reconstruction, and more. Secondly, the paper provides a framework for building new algorithms: depending on the way the variational bound is expressed we introduce prior-contrastive and joint-contrastive methods, and show practical inference algorithms based on either density ratio estimation or denoising.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 10; 2023: 10; 2024: 7; 2025: 2; 2026: 5.

39 papers.

Sort:

By area:

  1. 2022Causal Confusion and Reward Misidentification in Preference-Based Reward Learningcited by 52
  2. 2024Estimating Epistemic and Aleatoric Uncertainty with a Single Modelcited by 52
  3. 2023Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEscited by 48
  4. 2021Posterior Meta-Replay for Continual Learningcited by 45
  5. 2022Variational methods for simulation-based inferencecited by 43
  6. 2022Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoderscited by 42
  7. 2022GATSBI: Generative Adversarial Training for Simulation-Based Inferencecited by 36
  8. 2021Is MC Dropout Bayesian?cited by 35
  9. 2022The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Modelscited by 31
  10. 2021Adversarial and Contrastive Variational Autoencoder for Sequential Recommendationcited by 28
  11. 2024Training Neural Samplers with Reverse Diffusive KL Divergencecited by 21
  12. 2023Semi-Implicit Variational Inference via Score Matchingcited by 19
27 more
  1. 2021Variational inference with a quantum computercited by 18
  2. 2023Learning to Jump: Thinning and Thickening Latent Counts for Generative Modelingcited by 15
  3. 2023Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Accelerationcited by 14
  4. 2024A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Sciencecited by 14
  5. 2022Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utilitycited by 12
  6. 2023Neural Markov Jump Processescited by 11
  7. 2022Fat-Tailed Variational Inference with Anisotropic Tail Adaptive Flowscited by 10
  8. 2021Efficient Semi-Implicit Variational Inferencecited by 9
  9. 2024Kernel Semi-Implicit Variational Inferencecited by 8
  10. 2025DiffRatio: Training One-Step Diffusion Models Without Teacher Supervisioncited by 8
  11. 2022Gromov-Wasserstein Autoencoderscited by 7
  12. 2024Particle Semi-Implicit Variational Inferencecited by 7
  13. 2023Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processescited by 6
  14. 2022Generative Bayesian Inference with GANscited by 5
  15. 2023Implicit Variational Inference for High-Dimensional Posteriorscited by 5
  16. 2023Symmetric Equilibrium Learning of VAEscited by 3
  17. 2023Learning beyond sensations: how dreams organize neuronal representationscited by 2
  18. 2023Quantifying Assistive Robustness Via the Natural-Adversarial Frontiercited by 1
  19. 2024SoftCVI: Contrastive variational inference with self-generated soft labelscited by 1
  20. 2024Variational Bayesian Phylogenetic Inference with Semi-implicit Branch Length Distributionscited by 1
  21. 2025VarDiU: A Variational Diffusive Upper Bound for One-Step Diffusion Distillationcited by 1
  22. 2026A Kernel Approach for Semi-implicit Variational Inferencecited by 1
  23. 2022Bayesian Neural Network Inference via Implicit Models and the Posterior Predictive Distributioncited by 0
  24. 2026Large-scale empirical tuning and comparison of default optimizers for variational inferencecited by 0
  25. 2026Implicit Variational Rejection Samplingcited by 0
  26. 2026A Deep Generative Model for Synthesizing Labeled Wireless Signalscited by 0
  27. 2026IIns-VAE+: A Robust Transfer Learning Framework for Environmental Identification in Wireless Sensingcited by 0