PANOM: Automatic Hyper-Parameter Tuning for Inverse Problems
Abstract
Automated hyper-parameter tuning for unsupervised learning, including inverse problems, remains a long-standing open problem due to the lack of validation data. In this work, we design an automatic tuning criterion for inverse problems and formulate it as a bilevel optimization task. We demonstrate the efficiency of our tuning scheme on various inverse problems and different test and out-of-distribution image samples at no expense of performance drops.
Cite
Text
Liu et al. "PANOM: Automatic Hyper-Parameter Tuning for Inverse Problems." NeurIPS 2021 Workshops: Deep_Inverse, 2021.Markdown
[Liu et al. "PANOM: Automatic Hyper-Parameter Tuning for Inverse Problems." NeurIPS 2021 Workshops: Deep_Inverse, 2021.](https://mlanthology.org/neuripsw/2021/liu2021neuripsw-panom/)BibTeX
@inproceedings{liu2021neuripsw-panom,
title = {{PANOM: Automatic Hyper-Parameter Tuning for Inverse Problems}},
author = {Liu, Tianci and Zhang, Quan and Lei, Qi},
booktitle = {NeurIPS 2021 Workshops: Deep_Inverse},
year = {2021},
url = {https://mlanthology.org/neuripsw/2021/liu2021neuripsw-panom/}
}