Diffusion map particle systems for generative modeling
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 corresponding 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.
Oct-30-2023
- Country:
- North America > United States > Massachusetts (0.28)
- Genre:
- Research Report (0.50)
- Industry:
- Government > Regional Government (0.46)
- Health & Medicine (0.68)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks (1.00)
- Natural Language (0.95)
- Representation & Reasoning (1.00)
- Vision (0.93)
- Information Technology > Artificial Intelligence