mlsanityData to 14 Oct 2026

Coupled Variational Autoencoder

arXiv 2306.02565 ↗First posted 5 Jun 2023stat.ML cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Variational auto-encoders are powerful probabilistic models in generative tasks but suffer from generating low-quality samples which are caused by the holes in the prior. We propose the Coupled Variational Auto-Encoder (C-VAE), which formulates the VAE problem as one of Optimal Transport (OT) between the prior and data distributions. The C-VAE allows greater flexibility in priors and natural resolution of the prior hole problem by enforcing coupling between the prior and the data distribution and enables flexible optimization through the primal, dual, and semi-dual formulations of entropic OT. Simulations on synthetic and real data show that the C-VAE outperforms alternatives including VAE, WAE, and InfoVAE in fidelity to the data, quality of the latent representation, and in quality of generated samples.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 30 of its 41 references that are in the map. First posted on arXiv 5 Jun 2023.

Builds on

30 of 41 references.

References · 30

  1. 2017Neural Discrete Representation Learningcited by 4,712
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  4. 2015Variational Inference with Normalizing Flowscited by 2,170
  5. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,387
  6. 2021VideoGPT: Video Generation using VQ-VAE and Transformerscited by 658
  7. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  8. 2020Jukebox: A Generative Model for Musiccited by 542
  9. 2014Semi-Supervised Learning with Deep Generative Modelscited by 496
  10. 2015Importance Weighted Autoencoderscited by 456
  11. 2015Adversarial Autoencoderscited by 364
  12. 2017Learning Generative Models with Sinkhorn Divergencescited by 314
18 more
  1. 2017VAE with a VampPriorcited by 248
  2. 2016Adversarially Learned Inferencecited by 216
  3. 2019Diagnosing and Enhancing VAE Modelscited by 193
  4. 2016Stochastic Optimization for Large-scale Optimal Transportcited by 189
  5. 2018Hyperspherical Variational Auto-Encoderscited by 189
  6. 2017Large-Scale Optimal Transport and Mapping Estimationcited by 123
  7. 2018Generative Modeling using the Sliced Wasserstein Distancecited by 108
  8. 2021Generative Modeling with Optimal Transport Mapscited by 82
  9. 2019Semi-Supervised Learning with Normalizing Flowscited by 76
  10. 2018Molecular generative model based on conditional variational autoencoder for de novo molecular designcited by 73
  11. 2018Gaussian Process Prior Variational Autoencoderscited by 72
  12. 2020A Contrastive Learning Approach for Training Variational Autoencoder Priorscited by 66
  13. 2018SOM-VAE: Interpretable Discrete Representation Learning on Time Seriescited by 60
  14. 2017Towards Deeper Understanding of Variational Autoencoding Modelscited by 56
  15. 2018Discriminator Rejection Samplingcited by 49
  16. 2019Dirichlet Variational Autoencodercited by 43
  17. 2018Variational Autoencoder with Implicit Optimal Priorscited by 33
  18. 2017Multi-Stage Variational Auto-Encoders for Coarse-to-Fine Image Generationcited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 0; 2026: 3.

6 papers.

  1. 2024Paired Wasserstein Autoencoders for Conditional Samplingcited by 5
  2. 2026Var-JEPA: A Variational Formulation of the Joint-Embedding Predictive Architecture - Bridging Predictive and Generative Self-Supervised Learningcited by 4
  3. 2024On Kernel-based Variational Autoencodercited by 2
  4. 2024Diff-PCC: Diffusion-based Neural Compression for 3D Point Cloudscited by 2
  5. 2026MixFlow: Mixed Source Distributions Improve Rectified Flowscited by 1
  6. 2026A Multi-stage Constrained Optimization Framework for Data-driven Problemscited by 0