mlsanityData to 14 Oct 2026

Semi-Implicit Variational Inference

arXiv 1805.11183 ↗First posted 28 May 2018stat.ML cs.LG stat.COcited by 55

Not on the map. Why?

Abstract (arXiv)

Semi-implicit variational inference (SIVI) is introduced to expand the commonly used analytic variational distribution family, by mixing the variational parameter with a flexible distribution. This mixing distribution can assume any density function, explicit or not, as long as independent random samples can be generated via reparameterization. Not only does SIVI expand the variational family to incorporate highly flexible variational distributions, including implicit ones that have no analytic density functions, but also sandwiches the evidence lower bound (ELBO) between a lower bound and an upper bound, and further derives an asymptotically exact surrogate ELBO that is amenable to optimization via stochastic gradient ascent. With a substantially expanded variational family and a novel optimization algorithm, SIVI is shown to closely match the accuracy of MCMC in inferring the posterior in a variety of Bayesian inference tasks.

Key facts. Cited by 55 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 3; 2022: 9; 2023: 13; 2024: 14; 2025: 13; 2026: 3.

55 papers.

Sort:

By area:

  1. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 214
  2. 2022GFlowNets and variational inferencecited by 106
  3. 2023Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunitiescited by 61
  4. 2022Probabilistic Conformal Prediction Using Conditional Random Samplescited by 47
  5. 2024Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Stepcited by 47
  6. 2022Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoderscited by 42
  7. 2023SeeGera: Self-supervised Semi-implicit Graph Variational Auto-encoders with Maskingcited by 23
  8. 2024Score Forgetting Distillation: A Swift, Data-Free Method for Machine Unlearning in Diffusion Modelscited by 23
  9. 2024Training Neural Samplers with Reverse Diffusive KL Divergencecited by 21
  10. 2023Semi-Implicit Variational Inference via Score Matchingcited by 19
  11. 2023Learning to Jump: Thinning and Thickening Latent Counts for Generative Modelingcited by 18
  12. 2023Beta Diffusioncited by 17
38 more
  1. 2023Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Accelerationcited by 14
  2. 2022Latent State Marginalization as a Low-cost Approach for Improving Explorationcited by 13
  3. 2023Star-Shaped Denoising Diffusion Probabilistic Modelscited by 13
  4. 2024Guided Score identity Distillation for Data-Free One-Step Text-to-Image Generationcited by 13
  5. 2023Neural Markov Jump Processescited by 12
  6. 2025Few-Step Diffusion via Score identity Distillationcited by 12
  7. 2021Efficient Semi-Implicit Variational Inferencecited by 9
  8. 2024Kernel Semi-Implicit Variational Inferencecited by 8
  9. 2021Structured Dropout Variational Inference for Bayesian Neural Networkscited by 7
  10. 2024Particle Semi-Implicit Variational Inferencecited by 7
  11. 2024On Divergence Measures for Training GFlowNetscited by 6
  12. 2023Implicit Variational Inference for High-Dimensional Posteriorscited by 5
  13. 2023Wasserstein Gradient Flow over Variational Parameter Space for Variational Inferencecited by 5
  14. 2025CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Modelscited by 5
  15. 2021Interpolating between sampling and variational inference with infinite stochastic mixturescited by 3
  16. 2022PAVI: Plate-Amortized Variational Inferencecited by 2
  17. 2024Diffusion Boosted Treescited by 2
  18. 2024BayesCNS: A Unified Bayesian Approach to Address Cold Start and Non-Stationarity in Search Systems at Scalecited by 2
  19. 2025Fisher meets Feynman: score-based variational inference with a product of expertscited by 2
  20. 2022VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognitioncited by 1
  21. 2023Parameter Estimation in DAGs from Incomplete Data via Optimal Transportcited by 1
  22. 2023PAVI: Plate-Amortized Variational Inferencecited by 1
  23. 2023Variational Graph Autoencoder for Heterogeneous Information Networks with Missing and Inaccurate Attributescited by 1
  24. 2024Variational Bayesian Phylogenetic Inference with Semi-implicit Branch Length Distributionscited by 1
  25. 2024Scalable Weibull Graph Attention Autoencoder for Modeling Document Networkscited by 1
  26. 2024Semi-Implicit Functional Gradient Flow for Efficient Samplingcited by 1
  27. 2025Bayesian Computation in Deep Learningcited by 1
  28. 2025Particle Dynamics for Latent-Variable Energy-Based Modelscited by 1
  29. 2025Bayesian Semiparametric Causal Inference: Targeted Doubly Robust Estimation of Treatment Effectscited by 1
  30. 2026A Kernel Approach for Semi-implicit Variational Inferencecited by 1
  31. 2022Variational Inference for Bayesian Bridge Regressioncited by 0
  32. 2022Cyclical Kernel Adaptive Metropoliscited by 0
  33. 2022Bayesian Neural Network Inference via Implicit Models and the Posterior Predictive Distributioncited by 0
  34. 2024Towards Model-Agnostic Posterior Approximation for Fast and Accurate Variational Autoencoderscited by 0
  35. 2025Multi-resolution Score-Based Variational Graphical Diffusion for Causal Disaster System Modeling and Inferencecited by 0
  36. 2025A Generative Framework for Causal Estimation via Importance-Weighted Diffusion Distillationcited by 0
  37. 2025Revisiting Unbiased Implicit Variational Inferencecited by 0
  38. 2025Semi-Implicit Variational Inference via Kernelized Path Gradient Descentcited by 0

50 most cited of 55 All 55 (JSON)