mlsanityData to 14 Oct 2026

Unbiased Implicit Variational Inference

arXiv 1808.02078 ↗First posted 6 Aug 2018stat.ML cs.LGcited by 33

Not on the map. Why?

Abstract (arXiv)

We develop unbiased implicit variational inference (UIVI), a method that expands the applicability of variational inference by defining an expressive variational family. UIVI considers an implicit variational distribution obtained in a hierarchical manner using a simple reparameterizable distribution whose variational parameters are defined by arbitrarily flexible deep neural networks. Unlike previous works, UIVI directly optimizes the evidence lower bound (ELBO) rather than an approximation to the ELBO. We demonstrate UIVI on several models, including Bayesian multinomial logistic regression and variational autoencoders, and show that UIVI achieves both tighter ELBO and better predictive performance than existing approaches at a similar computational cost.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). First posted on arXiv 6 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 5; 2023: 9; 2024: 7; 2025: 4; 2026: 4.

33 papers.

Sort:

By area:

  1. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 214
  2. 2023Semi-Implicit Variational Inference via Score Matchingcited by 19
  3. 2023Learning to Jump: Thinning and Thickening Latent Counts for Generative Modelingcited by 18
  4. 2021On Out-of-distribution Detection with Energy-based Modelscited by 17
  5. 2023Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Accelerationcited by 14
  6. 2024A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Sciencecited by 14
  7. 2021A prior-based approximate latent Riemannian metriccited by 11
  8. 2021Efficient Semi-Implicit Variational Inferencecited by 9
  9. 2023Quantum HyperNetworks: Training Binary Neural Networks in Quantum Superpositioncited by 8
  10. 2024Kernel Semi-Implicit Variational Inferencecited by 8
  11. 2024Particle Semi-Implicit Variational Inferencecited by 7
  12. 2022Generative Bayesian Inference with GANscited by 6
21 more
  1. 2023Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processescited by 6
  2. 2023Implicit Variational Inference for High-Dimensional Posteriorscited by 5
  3. 2022PAVI: Plate-Amortized Variational Inferencecited by 2
  4. 2022Langevin Autoencoders for Learning Deep Latent Variable Modelscited by 2
  5. 2025Fisher meets Feynman: score-based variational inference with a product of expertscited by 2
  6. 2022VFDS: Variational Foresight Dynamic Selection in Bayesian Neural Networks for Efficient Human Activity Recognitioncited by 1
  7. 2023Master's Thesis: Out-of-distribution Detection with Energy-based Modelscited by 1
  8. 2023Parameter Estimation in DAGs from Incomplete Data via Optimal Transportcited by 1
  9. 2023PAVI: Plate-Amortized Variational Inferencecited by 1
  10. 2024Variational Bayesian Phylogenetic Inference with Semi-implicit Branch Length Distributionscited by 1
  11. 2024Semi-Implicit Functional Gradient Flow for Efficient Samplingcited by 1
  12. 2026A Kernel Approach for Semi-implicit Variational Inferencecited by 1
  13. 2021Deep Probabilistic Graphical Modelingcited by 0
  14. 2022Bayesian Neural Network Inference via Implicit Models and the Posterior Predictive Distributioncited by 0
  15. 2024Pathwise Gradient Variance Reduction with Control Variates in Variational Inferencecited by 0
  16. 2025Revisiting Unbiased Implicit Variational Inferencecited by 0
  17. 2025Semi-Implicit Variational Inference via Kernelized Path Gradient Descentcited by 0
  18. 2025Continuous Semi-Implicit Modelscited by 0
  19. 2026Variational Learning of Fractional Posteriorscited by 0
  20. 2026Large-scale empirical tuning and comparison of default optimizers for variational inferencecited by 0
  21. 2026Implicit Variational Rejection Samplingcited by 0