Model-free filtering in high dimensions via projection and score-based diffusions
- DiffM
We consider the problem of recovering a latent signal from its noisy observation . The unknown law of , and in particular its support , are accessible only through a large sample of i.i.d.\ observations. We further assume to be a low-dimensional submanifold of a high-dimensional Euclidean space . As a filter or denoiser , we suggest an estimator of the metric projection of onto the manifold . To compute this estimator, we study an auxiliary semiparametric model in which is obtained by adding isotropic Laplace noise to . Using score matching within a corresponding diffusion model, we obtain an estimator of the Bayesian posterior in this setup. Our main theoretical results show that, in the limit of high dimension , this posterior is concentrated near the desired metric projection .
View on arXiv