Posterior Temperature Optimization in Variational Inference for Inverse Problems
Not on the map. Why?
Abstract (arXiv)
Bayesian methods feature useful properties for solving inverse problems, such as tomographic reconstruction. The prior distribution introduces regularization, which helps solving the ill-posed problem and reduces overfitting. In practice, this often results in a suboptimal posterior temperature and the full potential of the Bayesian approach is not realized. In this paper, we optimize both the parameters of the prior distribution and the posterior temperature using Bayesian optimization. Well-tempered posteriors lead to better predictive performance and improved uncertainty calibration, which we demonstrate for the task of sparse-view CT reconstruction.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 12 of its 18 references that are in the map. First posted on arXiv 11 Jun 2021.
Builds on
12 of 18 references.
References · 12
- 2016Variational Inference: A Review for Statisticianscited by 1,466
- 2017Deep Image Priorcited by 1,097
- 2018A Tutorial on Bayesian Optimizationcited by 734
- 2018GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Accelerationcited by 603
- 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
- 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
- 2015Scalable Bayesian Optimization Using Deep Neural Networkscited by 284
- 2020Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methodscited by 56
- 2020A statistical theory of cold posteriors in deep neural networkscited by 53
- 2019A Bayesian Perspective on the Deep Image Priorcited by 52
- 2019Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inferencecited by 35
- 2020Uncertainty Estimation in Medical Image Denoising with Bayesian Deep Image Priorcited by 18
Built on by
Citing papers per year: 2022: 2; 2023: 0; 2024: 1.
3 papers.