Picture for Benjamin J. Zhang

Benjamin J. Zhang

Equivariant score-based generative models provably learn distributions with symmetries efficiently

Add code
Oct 02, 2024
Viaarxiv icon

Combining Wasserstein-1 and Wasserstein-2 proximals: robust manifold learning via well-posed generative flows

Add code
Jul 16, 2024
Viaarxiv icon

Score-based generative models are provably robust: an uncertainty quantification perspective

Add code
May 24, 2024
Viaarxiv icon

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

Add code
Feb 09, 2024
Viaarxiv icon

A mean-field games laboratory for generative modeling

Add code
May 06, 2023
Viaarxiv icon

Transport map unadjusted Langevin algorithms

Add code
Feb 28, 2023
Viaarxiv icon

Geometry-informed irreversible perturbations for accelerated convergence of Langevin dynamics

Add code
Aug 18, 2021
Figure 1 for Geometry-informed irreversible perturbations for accelerated convergence of Langevin dynamics
Figure 2 for Geometry-informed irreversible perturbations for accelerated convergence of Langevin dynamics
Figure 3 for Geometry-informed irreversible perturbations for accelerated convergence of Langevin dynamics
Figure 4 for Geometry-informed irreversible perturbations for accelerated convergence of Langevin dynamics
Viaarxiv icon