mlsanityData to 7 Oct 2026

Towards Deeper Understanding of Variational Autoencoding Models

arXiv 1702.08658 ↗First posted 28 Feb 2017cs.LG stat.MLcited by 56

Not on the map. Why?

Abstract (arXiv)

We propose a new family of optimization criteria for variational auto-encoding models, generalizing the standard evidence lower bound. We provide conditions under which they recover the data distribution and learn latent features, and formally show that common issues such as blurry samples and uninformative latent features arise when these conditions are not met. Based on these new insights, we propose a new sequential VAE model that can generate sharp samples on the LSUN image dataset based on pixel-wise reconstruction loss, and propose an optimization criterion that encourages unsupervised learning of informative latent features.

Key facts. Cited by 56 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Feb 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 20; 2022: 15; 2023: 9; 2024: 4; 2025: 3; 2026: 4.

56 papers.

Sort:

By area:

  1. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  2. 2019Variational Mixture-of-Experts Autoencoders for Multi-Modal Deep Generative Modelscited by 177
  3. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 165
  4. 2021High-Fidelity Pluralistic Image Completion with Transformerscited by 134
  5. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
  6. 2022HyperImpute: Generalized Iterative Imputation with Automatic Model Selectioncited by 81
  7. 2021Diverse Image Inpainting with Bidirectional and Autoregressive Transformerscited by 80
  8. 2021Greedy Hierarchical Variational Autoencoders for Large-Scale Video Predictioncited by 75
  9. 2023ReMasker: Imputing Tabular Data with Masked Autoencodingcited by 35
  10. 2021Towards Defending against Adversarial Examples via Attack-Invariant Featurescited by 25
  11. 2021Factor Analysis, Probabilistic Principal Component Analysis, Variational Inference, and Variational Autoencoder: Tutorial and Surveycited by 21
  12. 2021Creativity and Machine Learning: A Surveycited by 21
38 more
  1. 2021A deep generative model for probabilistic energy forecasting in power systems: normalizing flowscited by 18
  2. 2023DICE: Diverse Diffusion Model with Scoring for Trajectory Predictioncited by 18
  3. 2022Astronomia ex machina: a history, primer, and outlook on neural networks in astronomycited by 17
  4. 2023Precipitation Downscaling with Spatiotemporal Video Diffusioncited by 16
  5. 2024Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inferencecited by 15
  6. 2025Simulating the Visual World with Artificial Intelligence: A Roadmapcited by 15
  7. 2022Hierarchical Latent Structure for Multi-Modal Vehicle Trajectory Forecastingcited by 14
  8. 2021Cauchy-Schwarz Regularized Autoencodercited by 13
  9. 2021TopicNet: Semantic Graph-Guided Topic Discoverycited by 9
  10. 2021Compositional Learning-based Planning for Vision POMDPscited by 8
  11. 2022An Adaptive Federated Relevance Framework for Spatial Temporal Graph Learningcited by 7
  12. 2022PAEDID: Patch Autoencoder Based Deep Image Decomposition For Pixel-level Defective Region Segmentationcited by 6
  13. 2022Hierarchical Residual Learning Based Vector Quantized Variational Autoencoder for Image Reconstruction and Generationcited by 6
  14. 2023Coupled Variational Autoencodercited by 6
  15. 2023Leveraging Variational Autoencoders for Parameterized MMSE Estimationcited by 6
  16. 2024Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compressioncited by 6
  17. 2021Spread Flows for Manifold Modellingcited by 4
  18. 2022Continual Learning with Invertible Generative Modelscited by 3
  19. 2022Deterministic training of generative autoencoders using invertible layerscited by 3
  20. 2022Compositional Mixture Representations for Vision and Textcited by 3
  21. 2021Self-Supervised Delineation of Geological Structures using Orthogonal Latent Space Projectioncited by 2
  22. 2023Variational Diffusion Auto-encoder: Latent Space Extraction from Pre-trained Diffusion Modelscited by 2
  23. 2024SUICA: Learning Super-high Dimensional Sparse Implicit Neural Representations for Spatial Transcriptomicscited by 2
  24. 2021Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAEcited by 1
  25. 2022Multi-modal data generation with a deep metric variational autoencodercited by 1
  26. 2022Variational Autoencoders Without the Variationcited by 1
  27. 2022A Structure-Guided Diffusion Model for Large-Hole Image Completioncited by 1
  28. 2025Generative AI Meets Wireless Sensing: Towards Wireless Foundation Modelcited by 1
  29. 2026CEPAE: Conditional Entropy-Penalized Autoencoders for Time Series Counterfactualscited by 1
  30. 2026Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learningcited by 1
  31. 2021Deep Probabilistic Graphical Modelingcited by 0
  32. 2021Meta-learning Amidst Heterogeneity and Ambiguitycited by 0
  33. 2021The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoderscited by 0
  34. 2021LDC-VAE: A Latent Distribution Consistency Approach to Variational AutoEncoderscited by 0
  35. 2021Challenging the Semi-Supervised VAE Framework for Text Classificationcited by 0
  36. 2022CommsVAE: Learning the brain's macroscale communication dynamics using coupled sequential VAEscited by 0
  37. 2022Generalizing Multimodal Variational Methods to Setscited by 0
  38. 2023Interpretable Sentence Representation with Variational Autoencoders and Attentioncited by 0

50 most cited of 56 All 56 (JSON)