Generative Modeling by Minimizing the Wasserstein-2 Loss

arXiv:2406.13619 · stat.ML, cs.LG · Submitted 2024-06-19 · Read on arXiv

stat.ML, cs.LG

Submitted: 2024-06-19

Updated: 2026-08-25

Journal ref: SIAM Journal on Mathematics of Data Science, Vol. 6 (2026), No. 3, pp. 973-999

DOI: 10.1137/24M167559X

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Gradient Flow — 52× in this paper · explained in 2 episodes
• Optimal Transport — 22× in this paper · explained in 5 episodes
• Accuracy — 9× in this paper · explained in 1 episode
• Adaptation — 6× in this paper · explained in 1 episode
• Domain Adaptation — 6× in this paper · explained in 5 episodes
• Generative Modeling — 5× in this paper · explained in 3 episodes
• Wasserstein Distance — 5× in this paper · explained in 4 episodes
• Generative Model — 4× in this paper · explained in 2 episodes
• Stochastic Gradient Descent (SGD) — 2× in this paper · explained in 5 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Diffusion Processes — 1× in this paper · explained in 2 episodes
• Generative Adversarial Networks (GANs) — 1× in this paper · explained in 3 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes

Sources

• Faster SGD training by minibatch persistency
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Mean-Field Langevin Diffusions with Density-dependent Temperature
• Adversarial Computation of Optimal Transport Maps

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• Efficient quadratic entropy with distance sketches
• Embedding-Bias in Conditional Independence Testing
• From Log-Odds to Shapley Values: An Explanatory Geometry for the Weighted Naive Bayes Classifier