paper-with-me

홈 › Papers

Solving Bayesian Inverse Problems via Variational Autoencoders

2019-12-05 · Hwan Goh, Sheroze Sheriffdeen, Jonathan Wittmer, Tan Bui-Thanh

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.

📄 PDF Abstract BibTeX arXiv:1912.04212

Code (0)

등록된 구현이 없습니다.

Tasks

Uncertainty QuantificationVariational Inference

Methods 이 논문이 사용한 방법론

Solana Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Enhanced uncertainty quantification variational autoencoders for the solution of Bayesian inverse problems

2025-02-18 · Andrea Tonini, Luca Dede'

Among other uses, neural networks are a powerful tool for solving deterministic and Bayesian inverse problems in real-time. In the Bayesian framework, variational autoencoders, a specialized type of neural network, enabl…

Uncertainty Quantification

Utilizing variational autoencoders in the Bayesian inverse problem of photoacoustic tomography

2022-04-13 · Teemu Sahlström, Tanja Tarvainen

There has been an increasing interest in utilizing machine learning methods in inverse problems and imaging. Most of the work has, however, concentrated on image reconstruction problems, and the number of studies regardi…

BIG-bench Machine LearningImage Reconstruction

Half-VAE: An Encoder-Free VAE to Bypass Explicit Inverse Mapping

2024-09-06 · Yuan-Hao Wei, Yan-Jie Sun, Chen Zhang

Inference and inverse problems are closely related concepts, both fundamentally involving the deduction of unknown causes or parameters from observed data. Bayesian inference, a powerful class of methods, is often employ…

Bayesian InferenceCausal InferenceVariational Inference

Weak neural variational inference for solving Bayesian inverse problems without forward models: applications in elastography

2024-07-30 · Vincent C. Scholz, Yaohua Zang, Phaedon-Stelios Koutsourelakis

In this paper, we introduce a novel, data-driven approach for solving high-dimensional Bayesian inverse problems based on partial differential equations (PDEs), called Weak Neural Variational Inference (WNVI). The method…

Variational Inference

Variational Gaussian Processes For Linear Inverse Problems

2023-11-01 · NeurIPS 2023 11

By now Bayesian methods are routinely used in practice for solving inverse problems. In inverse problems the parameter or signal of interest is observed only indirectly, as an image of a given map, and the observations a…

Gaussian Processes