Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Structured Probabilistic Inference and Generative Modeling

Diffusion map particle systems for generative modeling

Fengyi Li · Youssef Marzouk

Keywords: [ generative modeling ] [ Kernel Methods ] [ gradient flows ] [ sampling ] [ diffusion maps ]


Abstract:

We propose a novel diffusion map particle system (DMPS) for generative modeling, based on diffusion maps and Laplacian-adjusted Wasserstein gradient descent (LAWGD). Diffusion maps are used to approximate the generator of the Langevin diffusion process from samples, and hence to learn the underlying data-generating manifold. On the other hand, LAWGD enables efficient sampling from the target distribution given a suitable choice of kernel, which we construct here via a spectral approximation of the generator, computed with diffusion maps. Our method requires no offline training and minimal tuning, and can outperform other approaches on data sets of moderate dimension.

Chat is not available.