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

Documenti analoghi

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