ASPIRE: iterative amortized posterior inference for Bayesian inverse problems
Open Access
- 14 March 2025
- journal article
- Published by IOP Publishing in Inverse Problems
- Vol. 41 (4) , 045001
Abstract
Due to their uncertainty quantification, Bayesian solutions to inverse problems are the framework of choice in applications that are risk averse. These benefits come at the cost of computations that are in general, intractable. New advances in machine learning and variational inference (VI) have lowered this computational barrier by leveraging data-driven learning. Two VI paradigms have emerged that represent different tradeoffs: amortized and non-amortized. Amortized VI can produce fast results but due to generalizing to many observed datasets it produces suboptimal inference results. Non-amortized VI is slower at inference but finds better posterior approximations since it is specialized towards a single observed dataset. Current amortized VI techniques run into a sub-optimality wall that cannot be improved without more expressive neural networks or extra training data. We present a solution that enables iterative improvement of amortized posteriors that uses the same networks architectures and training data. The benefits of our method requires extra computations but these remain frugal since they are based on physics-hybrid methods and summary statistics. Importantly, these computations remain mostly offline thus our method maintains cheap and reusable online evaluation while bridging the optimality gap between these two paradigms. We denote our proposed method ASPIRE - Amortized posteriors with Summaries that are Physics-based and Iteratively REfined. We first validate our method on a stylized problem with a known posterior then demonstrate its practical use on a high-dimensional and nonlinear transcranial medical imaging problem with ultrasound. Compared with the baseline and previous methods in the literature, ASPIRE stands out as an computationally efficient and high-fidelity method for posterior inference.Keywords
All Related Versions
Funding Information
- ML4Seismic
- Georgia Research Alliance
This publication has 47 references indexed in Scilit:
- Dual-Probe Transcranial Full-Waveform Inversion: A Brain Phantom Feasibility StudyUltrasound in Medicine & Biology, 2023
- 3-D Bayesian variational full waveform inversionGeophysical Journal International, 2023
- Uncertainty quantification for regularized inversion of electromagnetic geophysical data—Part I: motivation and theoryGeophysical Journal International, 2022
- A probabilistic approach to tomography and adjoint state methods, with an application to full waveform inversion in medical ultrasoundInverse Problems, 2022
- Bayesian seismic tomography using normalizing flowsGeophysical Journal International, 2021
- Full-waveform inversion imaging of the human brainnpj Digital Medicine, 2020
- Mitigating local minima in full-waveform inversion by expanding the search spaceGeophysical Journal International, 2013
- Massive lossless data compression and multiple parameter estimation from galaxy spectraMonthly Notices of the Royal Astronomical Society, 2000
- An Introduction to Variational Methods for Graphical ModelsMachine Learning, 1999
- Accurate Approximations for Posterior Moments and Marginal DensitiesJournal of the American Statistical Association, 1986