Bayesian BiLO: Bilevel Local Operator Learning for Efficient Uncertainty Quantification of Bayesian PDE Inverse Problems with Low-Rank Adaptation
Zhang, R. Z.; Miles, C. E.; Xie, X.; Lowengrub, J.
Show abstract
Uncertainty quantification in PDE inverse problems is essential in many applications. Scientific machine learning and AI enable data-driven learning of model components while preserving physical structure, and provide the scalability and adaptability needed for emerging imaging technologies and clinical insights. We develop a Bilevel Local Operator Learning framework for Bayesian inference in PDEs (B-BiLO). At the upper level, we sample parameters from the posterior via Hamiltonian Monte Carlo, while at the lower level we fine-tune a neural network via low-rank adaptation (LoRA) to approximate the solution operator locally. B-BiLO enables efficient gradient-based sampling without synthetic data or adjoint equations and avoids sampling in high-dimensional weight space, as in Bayesian neural networks, by optimizing weights deterministically. We analyze errors from approximate lower-level optimization and establish their impact on posterior accuracy. Numerical experiments across PDE models, including tumor growth, demonstrate that B-BiLO achieves accurate and efficient uncertainty quantification. MSC Classification: 65M32, 62F15, 68T07
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- LSMMD-MA: Scaling multimodal data integration for single-cell genomics data analysis 95%
- Efficient Exact Inference for Dynamical Systems with Noisy Measurements using Sequential Approximate Bayesian Computation 94%
- Quasi-Entropy Closure: A Fast and Reliable Approach to Close the Moment Equations of the Chemical Master Equation 94%
Similar papers in this journal
Similar papers in this journal
- Efficient construction of Markov state models for stochastic gene regulatory networks by domain decomposition 96%
- Transfer Learning Models for Bacterial Strain Dissemination Biomarkers using Weighted Non-Parallel Proximal Support Vector Machines 94%
- CBMOS: a GPU-enabled Python framework for the numerical study of center-based models 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.