mlsanityData to 7 Oct 2026

Distribution Matching in Variational Inference

arXiv 1802.06847 ↗First posted 19 Feb 2018stat.ML cs.LGcited by 35

Not on the map. Why?

Abstract (arXiv)

With the increasingly widespread deployment of generative models, there is a mounting need for a deeper understanding of their behaviors and limitations. In this paper, we expose the limitations of Variational Autoencoders (VAEs), which consistently fail to learn marginal distributions in both latent and visible spaces. We show this to be a consequence of learning by matching conditional distributions, and the limitations of explicit model and posterior distributions. It is popular to consider Generative Adversarial Networks (GANs) as a means of overcoming these limitations, leading to hybrids of VAEs and GANs. We perform a large-scale evaluation of several VAE-GAN hybrids and analyze the implications of class probability estimation for learning distributions. While promising, we conclude that at present, VAE-GAN hybrids have limited applicability: they are harder to scale, evaluate, and use for inference compared to VAEs; and they do not improve over the generation quality of GANs.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 7; 2023: 6; 2024: 2; 2025: 5; 2026: 6.

35 papers.

Sort:

By area:

  1. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  2. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 447
  3. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
  4. 2022Particle algorithms for maximum likelihood training of latent variable modelscited by 26
  5. 2021Distribution-Aware Testing of Neural Networks Using Generative Modelscited by 22
  6. 2021A survey on Variational Autoencoders from a GreenAI perspectivecited by 22
  7. 2023Calibration by Distribution Matching: Trainable Kernel Calibration Metricscited by 20
  8. 2025VCT: Training Consistency Models with Variational Noise Couplingcited by 15
  9. 2022Bottlenecks CLUB: Unifying Information-Theoretic Trade-offs Among Complexity, Leakage, and Utilitycited by 12
  10. 2022Comparing the latent space of generative modelscited by 11
  11. 2023FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generationcited by 9
  12. 2021Low-rank Characteristic Tensor Density Estimation Part II: Compression and Latent Density Estimationcited by 8
23 more
  1. 2021Variational Leakage: The Role of Information Complexity in Privacy Leakagecited by 6
  2. 2022Latent Space Diffusion Models of Cryo-EM Structurescited by 6
  3. 2023Matching aggregate posteriors in the variational autoencodercited by 6
  4. 2024Learning Latent Space Hierarchical EBM Diffusion Modelscited by 6
  5. 2025ARD-VAE: A Statistical Formulation to Find the Relevant Latent Dimensions of Variational Autoencoderscited by 6
  6. 2022From latent dynamics to meaningful representationscited by 5
  7. 2023Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectivescited by 4
  8. 2021Bayesian Distributional Policy Gradientscited by 3
  9. 2021Probabilistic Autoencoder using Fisher Informationcited by 3
  10. 2025CoVAE: Consistency Training of Variational Autoencoderscited by 3
  11. 2026Explorative Modeling: Unlocking a Third Pretraining Axis and End-to-End Generationcited by 3
  12. 2025Disentanglement Analysis in Deep Latent Variable Models Matching Aggregate Posterior Distributionscited by 1
  13. 2026Quartet of Diffusions: Structure-Aware Point Cloud Generation through Part and Symmetry Guidancecited by 1
  14. 2021Deep Dive into Semi-Supervised ELBO for Improving Classification Performancecited by 0
  15. 2022RENs: Relevance Encoding Networkscited by 0
  16. 2023Learning variational autoencoders via MCMC speed measurescited by 0
  17. 2023On Unsupervised Image-to-image translation and GAN stabilitycited by 0
  18. 2024Resultant: Incremental Effectiveness on Likelihood for Unsupervised Out-of-Distribution Detectioncited by 0
  19. 2025Unsupervised Anomaly Detection in Multivariate Time Series across Heterogeneous Domainscited by 0
  20. 2026Iterative Amortized Hierarchical VAEcited by 0
  21. 2026Molecular Design beyond Training Data with Novel Extended Objective Functionals of Generative AI Models Driven by Quantum Annealing Computercited by 0
  22. 2026eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributionscited by 0
  23. 2026Multi-Teacher Contrastive Distillation for Edge-Efficient Pathology Foundation Modelscited by 0