Affine invariant interacting Langevin dynamics for Bayesian inference
About
We propose a computational method (with acronym ALDI) for sampling from a given target distribution based on first-order (overdamped) Langevin dynamics which satisfies the property of affine invariance. The central idea of ALDI is to run an ensemble of particles with their empirical covariance serving as a preconditioner for their underlying Langevin dynamics. ALDI does not require taking the inverse or square root of the empirical covariance matrix, which enables application to high-dimensional sampling problems. The theoretical properties of ALDI are studied in terms of non-degeneracy and ergodicity. Furthermore, we study its connections to diffusion on Riemannian manifolds and Wasserstein gradient flows. Bayesian inference serves as a main application area for ALDI. In case of a forward problem with additive Gaussian measurement errors, ALDI allows for a gradient-free approximation in the spirit of the ensemble Kalman filter. A computational comparison between gradient-free and gradient-based ALDI is provided for a PDE constrained Bayesian inverse problem.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Synthetic Distribution Sampling | GMM2 | KSD0.93 | 7 | |
| Synthetic Distribution Sampling | Funnel20 | KSD28.66 | 7 | |
| Synthetic Distribution Sampling | Funnel10 | KSD20.34 | 7 | |
| Synthetic Distribution Sampling | GMM5 | KSD1.516 | 7 | |
| Synthetic Distribution Sampling | GMM10 | KSD2.185 | 7 | |
| Synthetic Distribution Sampling | Joker | KSD9.286 | 7 | |
| Synthetic Distribution Sampling | Funnel2 | KSD9.008 | 7 | |
| Synthetic Distribution Sampling | Funnel5 | KSD14.43 | 7 | |
| Synthetic Distribution Sampling | GMM20 | KSD3.355 | 7 | |
| Synthetic Distribution Sampling | Himmelblau | KSD14.33 | 6 |