mlsanityData to 7 Oct 2026

Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generation

arXiv 2302.11294 ↗First posted 22 Feb 2023stat.ML cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

The Gaussianity assumption has been consistently criticized as a main limitation of the Variational Autoencoder (VAE) despite its efficiency in computational modeling. In this paper, we propose a new approach that expands the model capacity (i.e., expressive power of distributional family) without sacrificing the computational advantages of the VAE framework. Our VAE model's decoder is composed of an infinite mixture of asymmetric Laplace distribution, which possesses general distribution fitting capabilities for continuous variables. Our model is represented by a special form of a nonparametric M-estimator for estimating general quantile functions, and we theoretically establish the relevance between the proposed model and quantile estimation. We apply the proposed model to synthetic data generation, and particularly, our model demonstrates superiority in easily adjusting the level of data privacy.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 34 of its 68 references that are in the map. First posted on arXiv 22 Feb 2023.

Builds on

34 of 68 references.

References · 34

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  4. 2016Variational Inference: A Review for Statisticianscited by 1,466
  5. 2019Modeling Tabular data using Conditional GANcited by 695
  6. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  7. 2017Generative Adversarial Networks: An Overviewcited by 588
  8. 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
  9. 2015Importance Weighted Autoencoderscited by 454
  10. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
  11. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  12. 2015Adversarial Autoencoderscited by 359
22 more
  1. 2017VAE with a VampPriorcited by 247
  2. 2017A General and Adaptive Robust Loss Functioncited by 236
  3. 2019Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Modelcited by 228
  4. 2017A Multi-Horizon Quantile Recurrent Forecastercited by 211
  5. 2020Focal Frequency Loss for Image Reconstruction and Synthesiscited by 204
  6. 2017Generating Multi-label Discrete Patient Records using Generative Adversarial Networkscited by 197
  7. 2019Diagnosing and Enhancing VAE Modelscited by 192
  8. 2018Data Synthesis based on Generative Adversarial Networkscited by 184
  9. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  10. 2019Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapsecited by 120
  11. 2019Improved Conditional VRNNs for Video Predictioncited by 104
  12. 2019Reliable training and estimation of variance networkscited by 63
  13. 2017Variational Approaches for Auto-Encoding Generative Adversarial Networkscited by 52
  14. 2019Topic-Guided Variational Autoencoders for Text Generationcited by 44
  15. 2020A Loss Function for Generative Neural Networks Based on Watson's Perceptual Modelcited by 39
  16. 2021Copula Flows for Synthetic Data Generationcited by 35
  17. 2020On Implicit Regularization in β-VAEscited by 34
  18. 2021Causal-TGAN: Generating Tabular Data Using Causal Generative Adversarial Networkscited by 12
  19. 2019Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacianscited by 9
  20. 2019Implicit Discriminator in Variational Autoencodercited by 5
  21. 2021Deep Quantile Regression for Uncertainty Estimation in Unsupervised and Supervised Lesion Detectioncited by 4
  22. 2020Addressing Variance Shrinkage in Variational Autoencoders using Quantile Regressioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 2; 2026: 1.

9 papers.

  1. 2024Distributional MIPLIB: a Multi-Domain Library for Advancing ML-Guided MILP Methodscited by 15
  2. 2024MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular Datacited by 7
  3. 2023Privacy Measurement in Tabular Synthetic Data: State of the Art and Future Research Directionscited by 4
  4. 2025Probabilistic bias adjustment of seasonal predictions of Arctic Sea Ice Concentrationcited by 2
  5. 2024Masked Language Modeling Becomes Conditional Density Estimation for Tabular Data Synthesiscited by 1
  6. 2026Toward generative machine learning for boosting ensembles of climate simulationscited by 1
  7. 2023Joint Distributional Learning via Cramer-Wold Distancecited by 0
  8. 2023Balanced Marginal and Joint Distributional Learning via Mixture Cramer-Wold Distancecited by 0
  9. 2025Likelihood-Free Variational Autoencoderscited by 0