mlsanityData to 14 Oct 2026

Implicit Variational Rejection Sampling

arXiv 2606.14235 ↗First posted 12 Jun 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Variational Inference (VI) is a fundamental inference technique in Bayesian machine learning for approximating complex posterior distributions. Traditional VI often relies on the mean-field factorization, which can inadequately capture true posterior complexity. Recent advancements have leveraged neural networks to model implicit distributions, offering increased flexibility. However, the practical constraints of neural network architectures still produces inaccuracies. In this paper, we propose a method called Implicit Variational Rejection Sampling (IVRS), which integrates implicit distributions with rejection sampling to improve the posterior approximation. Our method uses neural networks to construct implicit proposal distributions, and rejection sampling with a discriminator network that estimates the density ratio between the implicit proposal and the true posterior for refining the approximation. Towards this end, we introduce the Implicit Resampling Evidence Lower Bound (IR-ELBO) as a metric to characterize the resampled distribution's quality and derive a tighter variational lower bound. Experimental results demonstrate that our method outperforms traditional variational inference techniques.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 49 of its 66 references that are in the map. First posted on arXiv 12 Jun 2026.

Builds on

49 of 66 references.

References · 49

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Variational Inference with Normalizing Flowscited by 2,170
  3. 2019Generating Long Sequences with Sparse Transformerscited by 1,546
  4. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  5. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
  6. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 637
  7. 2015Importance Weighted Autoencoderscited by 456
  8. 2016Ladder Variational Autoencoderscited by 318
  9. 2020Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Imagescited by 264
  10. 2015DRAW: A Recurrent Neural Network For Image Generationcited by 191
  11. 2017Generalization and Equilibrium in Generative Adversarial Nets (GANs)cited by 166
  12. 2019BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modelingcited by 109
37 more
  1. 2017Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networkscited by 107
  2. 2019Preventing Posterior Collapse with delta-VAEscited by 86
  3. 2018Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscalingcited by 74
  4. 2018Resampled Priors for Variational Autoencoderscited by 57
  5. 2018Semi-Implicit Variational Inferencecited by 55
  6. 2021Consistency Regularization for Variational Auto-Encoderscited by 51
  7. 2018Discriminator Rejection Samplingcited by 49
  8. 2021Resampling Base Distributions of Normalizing Flowscited by 42
  9. 2017Variational Inference using Implicit Distributionscited by 39
  10. 2018Unbiased Implicit Variational Inferencecited by 33
  11. 2018DVAE++: Discrete Variational Autoencoders with Overlapping Transformationscited by 32
  12. 2019MaCow: Masked Convolutional Generative Flowcited by 32
  13. 2016Reparameterization Gradients through Acceptance-Rejection Sampling Algorithmscited by 22
  14. 2020Locally Masked Convolution for Autoregressive Modelscited by 22
  15. 2018Doubly Semi-Implicit Variational Inferencecited by 19
  16. 2023Semi-Implicit Variational Inference via Score Matchingcited by 19
  17. 2024Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational Inferencecited by 16
  18. 2019PixelVAE++: Improved PixelVAE with Discrete Priorcited by 15
  19. 2018Variational Rejection Samplingcited by 13
  20. 2025Dequantified Diffusion-Schr"odinger Bridge for Density Ratio Estimationcited by 11
  21. 2025EVODiff: Entropy-aware Variance Optimized Diffusion Inferencecited by 10
  22. 2021Efficient Semi-Implicit Variational Inferencecited by 9
  23. 2023Sparse Variational Student-t Processescited by 8
  24. 2024Kernel Semi-Implicit Variational Inferencecited by 8
  25. 2024Hierarchical VAE with a Diffusion-based VampPriorcited by 8
  26. 2023Bayesian Gaussian Process ODEs via Double Normalizing Flowscited by 7
  27. 2024Particle Semi-Implicit Variational Inferencecited by 7
  28. 2022Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoderscited by 6
  29. 2023Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processescited by 6
  30. 2023Optimal Budgeted Rejection Sampling for Generative Modelscited by 5
  31. 2024Fully Bayesian Differential Gaussian Processes through Stochastic Differential Equationscited by 4
  32. 2024Variational Learning of Gaussian Process Latent Variable Models through Stochastic Gradient Annealed Importance Samplingcited by 4
  33. 2025Diffusion Bridge Variational Inference for Deep Gaussian Processescited by 4
  34. 2024Efficient Mixture Learning in Black-Box Variational Inferencecited by 3
  35. 2023Reparameterized Variational Rejection Samplingcited by 2
  36. 2024Sparse Variational Student-t Processes for Heavy-tailed Modelingcited by 2
  37. 2024Flexible Bayesian Last Layer Models Using Implicit Priors and Diffusion Posterior Samplingcited by 1

Built on by

Not cited yet.