09A: Uncertainty Quantification
Materials:
Date: Tuesday, 24-Sep-2024
Pre-work:
In-Class
Post-class
- [paper] A tutorial on Conformal Prediction
- [paper] Towards Reliability using Pretrained Large Model Extensions
- [tools] awesome-conformal-prediction - a collection Conformal Prediction resources including implementations.
- [tools] crepes - Conformal Classifiers, Regressors, and Predictive Systems.
- [tools] TorchCP - a python toolbox for Conformal Prediction research in Deep Learning Models using PyTorch.
- [tools] MAPIE - a python toolbox for Conformal Prediction
- [tools] DEEL-PUNCC - a python toolbox for Conformal Prediction from DEEL.ai a project for Dependable, Certifiable, Explainable AI for Critical Systems. Checkout the sister projects from DEEl on Bias DEEL INFLUENCIAE, oodeel for OOD, xplique for XAI,
Notes
- Deep Learning models are not calibrated. They can make confident, but wrong mistakes.
- Conformal Prediction (CP) provides a rigorous statistical guarantees for the predictions by predicting sets and not points. For example, in a regression problem, one gets to predict an interval with guaranteed coverage probability. In a classification problem, CP may predict more than one class label.
- CP is model-agnostic and can work for a variety of tasks including, regression, multi-class classification, multi-label prediction, time-series models, and also useful in LLMs Conformal Language Modeling, even though it is still a research topic.
- It is a post-hoc technique and should be used in every project.