UCI-regression Experiments

Library of model configurations to make extended experiments on the UCI regression benchmark.

These model configurations will work until at least torch-uncertainty==0.10.1.

How to use this library

General command to train a model:

cd uci_datasets
python mlp.py fit --config configs/{dataset}/{network}/{dist_family}.yaml

Example:

cd uci_datasets
python mlp.py fit --config configs/kinn8nm/mlp/laplace.yaml

Citation

If you find this repository useful for your research, please consider citing

@inproceedings{lafage2025torch,
  title={Torch-Uncertainty: Deep Learning Uncertainty Quantification},
  author={Lafage, Adrien and Laurent, Olivier and Gabetni, Firas and Franchi, Gianni},
  booktitle={NeurIPS D&B}
  year={2025}
}