Model-free filtering in high dimensions via projection and score-based diffusions
By: Sören Christensen , Jan Kallsen , Claudia Strauch and more
Potential Business Impact:
Cleans up messy data to find hidden patterns.
We consider the problem of recovering a latent signal $X$ from its noisy observation $Y$. The unknown law $\mathbb{P}^X$ of $X$, and in particular its support $\mathscr{M}$, are accessible only through a large sample of i.i.d.\ observations. We further assume $\mathscr{M}$ to be a low-dimensional submanifold of a high-dimensional Euclidean space $\mathbb{R}^d$. As a filter or denoiser $\widehat X$, we suggest an estimator of the metric projection $\pi_{\mathscr{M}}(Y)$ of $Y$ onto the manifold $\mathscr{M}$. To compute this estimator, we study an auxiliary semiparametric model in which $Y$ is obtained by adding isotropic Laplace noise to $X$. Using score matching within a corresponding diffusion model, we obtain an estimator of the Bayesian posterior $\mathbb{P}^{X \mid Y}$ in this setup. Our main theoretical results show that, in the limit of high dimension $d$, this posterior $\mathbb{P}^{X\mid Y}$ is concentrated near the desired metric projection $\pi_{\mathscr{M}}(Y)$.
Similar Papers
MAD: Manifold Attracted Diffusion
Machine Learning (Stat)
Makes blurry pictures sharp and clear.
Nonparametric estimation of a factorizable density using diffusion models
Statistics Theory
Makes computers create realistic pictures and sounds.
Injecting Measurement Information Yields a Fast and Noise-Robust Diffusion-Based Inverse Problem Solver
Machine Learning (CS)
Makes blurry pictures clear using smart guessing.