Solving Bayesian Inverse Problems via Variational Autoencoders
arXiv:1912.04212
Abstract
In recent years, the field of machine learning has made phenomenal progress in the pursuit of simulating real-world data generation processes. One notable example of such success is the variational autoencoder (VAE). In this work, with a small shift in perspective, we leverage and adapt VAEs for a different purpose: uncertainty quantification in scientific inverse problems. We introduce UQ-VAE: a flexible, adaptive, hybrid data/model-informed framework for training neural networks capable of rapid modelling of the posterior distribution representing the unknown parameter of interest. Specifically, from divergence-based variational inference, our framework is derived such that most of the information usually present in scientific inverse problems is fully utilized in the training procedure. Additionally, this framework includes an adjustable hyperparameter that allows selection of the notion of distance between the posterior model and the target distribution. This introduces more flexibility in controlling how optimization directs the learning of the posterior model. Further, this framework possesses an inherent adaptive optimization property that emerges through the learning of the posterior uncertainty.
References in corpus (19)
- Auto-Encoding Variational Bayes
- Practical Bayesian Optimization of Machine Learning Algorithms
- Deep Convolutional Neural Network for Inverse Problems in Imaging
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
- Bayesian parameter estimation using conditional variational autoencoders for gravitational-wave astronomy
- Learning Bayesian posteriors with neural networks for gravitational-wave inference
- Geometric MCMC for Infinite-Dimensional Inverse Problems
- A learning-based method for solving ill-posed nonlinear inverse problems: a simulation study of Lung EIT
- Deeply Uncertain: Comparing Methods of Uncertainty Quantification in Deep Learning Algorithms
- Deep Bayesian Inversion
- Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction
- Physics-informed deep generative models
- A family of statistical symmetric divergences based on Jensen's inequality
- Projected Stein Variational Newton: A Fast and Scalable Bayesian Inference Method in High Dimensions
- From Deep to Physics-Informed Learning of Turbulence: Diagnostics
- Bayesian Inference with Generative Adversarial Network Priors
- hIPPYlib: An Extensible Software Framework for Large-Scale Inverse Problems Governed by PDEs; Part I: Deterministic Inversion and Linearized Bayesian Inference
- Solving Inverse Problems by Joint Posterior Maximization with a VAE Prior