Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Deep Adaptive Dimension Reduction for Bayesian Inference in Inverse Problems

About

Solving high-dimensional PDE-governed inverse problems is often challenging due to complex non-Gaussian posterior distributions, expensive forward model evaluations, and misspecified prior information. To address these issues, we propose a deep adaptive dimension-reduction Bayesian inference framework based on the Variational Flow (VF) model. Since standard normalizing flows are restricted by bijective mappings and cannot directly reduce dimensions, VF overcomes this limitation by integrating VAE-based nonlinear dimension reduction with dual normalizing flows for the latent prior and encoder. This design provides a strictly higher evidence lower bound than VAE and allows more flexible approximation of complex posterior distributions. We further introduce an iterative prior updating strategy that gradually moves the prior mean toward high-probability posterior regions, avoiding manual prior tuning. These components form a closed adaptive loop together with an adaptively fine-tuned Fourier Neural Operator (FNO) surrogate: VF generates posterior-concentrated samples to refine the surrogate, while the updated surrogate further improves posterior inference. Numerical experiments on a 100-dimensional Rosenbrock problem and three standard PDE-governed inverse problems show that our method delivers competitive or superior accuracy compared with MCMC, UKI, and SVGD baselines across all tested configurations, with the most pronounced advantages emerging in challenging scenarios such as high-noise observations and high-dimensional parameter spaces.

Yueyang Wang, Xili Wang, Kejun Tang, Xiaoliang Wan, Tao Zhou, Chao Yang• 2026

Related benchmarks

TaskDatasetResultRank
Bayesian Inverse Problem2D Navier-Stokes d=32
Relative Inversion Error (1% Noise)0.2849
5
Bayesian Inverse Problem2D Navier-Stokes d=64
Relative Inversion Error (1% Noise)28.79
5
Inverse Problem1D Darcy Flow d=32
Relative Inversion Error (1% Noise)22.92
5
Inverse Problem1D Darcy Flow d=64
Relative Inversion Error (1% Noise)0.2073
5
Showing 4 of 4 rows

Other info

Follow for update