A kernel formula for regularized Wasserstein proximal operators
Not on the map. Why?
Abstract (arXiv)
We study a class of regularized proximal operators in Wasserstein-2 space. We derive their solutions by kernel integration formulas. We obtain the Wasserstein proximal operator using a pair of forward-backward partial differential equations consisting of a continuity equation and a Hamilton-Jacobi equation with a terminal time potential function and an initial time density function. We regularize the PDE pair by adding forward and backward Laplacian operators. We apply Hopf-Cole type transformations to rewrite these regularized PDE pairs into forward-backward heat equations. We then use the fundamental solution of the heat equation to represent the regularized Wasserstein proximal with kernel integral formulas. Numerical examples show the effectiveness of kernel formulas in approximating the Wasserstein proximal operator.
Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 Jan 2023.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2023: 1; 2024: 4; 2025: 3; 2026: 3.
11 papers.
- 2024Wasserstein proximal operators describe score-based generative models and resolve memorizationcited by 14
- 2023Noise-Free Sampling Algorithms via Regularized Wasserstein Proximalscited by 7
- 2024Score-based Neural Ordinary Differential Equations for Computing Mean Field Control Problemscited by 7
- 2024Combining Wasserstein-1 and Wasserstein-2 proximals: robust manifold learning via well-posed generative flowscited by 4
- 2025Proximal optimal transport divergencescited by 3
- 2024HJ-sampler: A Bayesian sampler for inverse problems of a stochastic process by leveraging Hamilton-Jacobi PDEs and score-based generative modelscited by 2
- 2026Learn to Evolve: Self-supervised Neural JKO Operator for Wasserstein Gradient Flowcited by 2
- 2025Preconditioned Regularized Wasserstein Proximal Samplingcited by 1
- 2025Sparse Transformer Architectures via Regularized Wasserstein Proximal Operator with L1 Priorcited by 1
- 2026Accelerated Regularized Wasserstein Proximal Sampling Algorithmscited by 0
- 2026Constrained Flow Policy Updates: A Generalized Schr"odinger Bridge Viewcited by 0
- 2026Constrained Flow Policy Updates: A Generalized Schr"odinger Bridge View26 Sep 2026
- 2026Accelerated Regularized Wasserstein Proximal Sampling Algorithms14 Jan 2026
- 2026Learn to Evolve: Self-supervised Neural JKO Operator for Wasserstein Gradient Flow9 Jan 2026
- 2025Sparse Transformer Architectures via Regularized Wasserstein Proximal Operator with L1 Prior18 Oct 2025
- 2025Preconditioned Regularized Wasserstein Proximal Sampling1 Sep 2025
- 2025Proximal optimal transport divergences17 May 2025
- 2024Score-based Neural Ordinary Differential Equations for Computing Mean Field Control Problems24 Sep 2024
- 2024HJ-sampler: A Bayesian sampler for inverse problems of a stochastic process by leveraging Hamilton-Jacobi PDEs and score-based generative models15 Sep 2024
- 2024Combining Wasserstein-1 and Wasserstein-2 proximals: robust manifold learning via well-posed generative flows16 Jul 2024
- 2024Wasserstein proximal operators describe score-based generative models and resolve memorization9 Feb 2024
- 2023Noise-Free Sampling Algorithms via Regularized Wasserstein Proximals28 Aug 2023