Fortuna: A Library for Uncertainty Quantification in Deep Learning
This work addresses the need for reliable uncertainty estimates in deep learning for practitioners, though it is incremental as it packages existing methods into a library.
The authors tackled the problem of uncertainty quantification in deep learning by introducing Fortuna, an open-source library that supports calibration techniques like conformal prediction and scalable Bayesian inference, resulting in a tool that simplifies benchmarking and helps build robust AI systems.
We present Fortuna, an open-source library for uncertainty quantification in deep learning. Fortuna supports a range of calibration techniques, such as conformal prediction that can be applied to any trained neural network to generate reliable uncertainty estimates, and scalable Bayesian inference methods that can be applied to Flax-based deep neural networks trained from scratch for improved uncertainty quantification and accuracy. By providing a coherent framework for advanced uncertainty quantification methods, Fortuna simplifies the process of benchmarking and helps practitioners build robust AI systems.