Wasserstein proximal operators describe score-based generative models and resolve memorization

Documents similaires

• Probabilistic operator learning: generative modeling and uncertainty quantification for foundation models of differential equations
  par: Zhang, Benjamin J., et autres
  Publié: (2025)
• Equivariant score-based generative models provably learn distributions with symmetries efficiently
  par: Chen, Ziyu, et autres
  Publié: (2024)
• Combining Wasserstein-1 and Wasserstein-2 proximals: robust manifold learning via well-posed generative flows
  par: Gu, Hyemin, et autres
  Publié: (2024)
• Sparse Transformer Architectures via Regularized Wasserstein Proximal Operator with $L_1$ Prior
  par: Han, Fuqun, et autres
  Publié: (2025)
• Tensor train based sampling algorithms for approximating regularized Wasserstein proximal operators
  par: Han, Fuqun, et autres
  Publié: (2024)