mlsanityData to 14 Oct 2026

Wasserstein Variational Inference

arXiv 1805.11284 ↗First posted 29 May 2018stat.ML cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

This paper introduces Wasserstein variational inference, a new form of approximate Bayesian inference based on optimal transport theory. Wasserstein variational inference uses a new family of divergences that includes both f-divergences and the Wasserstein distance as special cases. The gradients of the Wasserstein variational loss are obtained by backpropagating through the Sinkhorn iterations. This technique results in a very stable likelihood-free training method that can be used with implicit distributions and probabilistic programs. Using the Wasserstein variational inference framework, we introduce several new forms of autoencoders and test their robustness and performance against existing variational autoencoding techniques.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 5; 2022: 2; 2023: 4; 2024: 1; 2025: 3; 2026: 1.

17 papers.

Sort:

By area:

  1. 2021A Survey on Optimal Transport for Machine Learning: Theory and Applicationscited by 35
  2. 2021Wasserstein Unsupervised Reinforcement Learningcited by 22
  3. 2020f-GAIL: Learning f-Divergence for Generative Adversarial Imitation Learningcited by 20
  4. 2022Sliced Wasserstein Variational Inferencecited by 18
  5. 2023On the Convergence of Coordinate Ascent Variational Inferencecited by 18
  6. 2022Gromov-Wasserstein Autoencoderscited by 7
  7. 2021Bayesian brains and the R'enyi divergencecited by 6
  8. 2021Evaluating Sensitivity to the Stick-Breaking Prior in Bayesian Nonparametricscited by 4
  9. 2023Hyperbolic Geometry in Computer Vision: A Surveycited by 4
  10. 2025Deep Generative Models: Complexity, Dimensionality, and Approximationcited by 4
  11. 2021Bayesian Distributional Policy Gradientscited by 3
  12. 2024A Primer on Variational Inference for Physics-Informed Deep Generative Modellingcited by 3
5 more
  1. 2025Bayesian Experimental Design for Model Discrepancy Calibration: An Auto-Differentiable Ensemble Kalman Inversion Approachcited by 2
  2. 2023Parameter Estimation in DAGs from Incomplete Data via Optimal Transportcited by 1
  3. 2023Nonlinear Kalman Filtering with Reparametrization Gradientscited by 0
  4. 2025Streaming Sliced Optimal Transportcited by 0
  5. 2026Bayesian Experimental Design for Model Discrepancy Calibration: A Rivalry between Kullback--Leibler Divergence and Wasserstein Distancecited by 0