Extending Conformal Prediction to Hidden Markov Models with Exact Validity via de Finetti's Theorem for Markov Chains

B Nettasinghe, S Chatterjee… - International …, 2023 - proceedings.mlr.press
Conformal prediction is a widely used method to quantify the uncertainty of a classifier under
the assumption of exchangeability (eg, IID data). We generalize conformal prediction to the …

Exact optimization of conformal predictors via incremental and decremental learning

G Cherubin, K Chatzikokolakis… - … Conference on Machine …, 2021 - proceedings.mlr.press
Conformal Predictors (CP) are wrappers around ML models, providing error guarantees
under weak assumptions on the data distribution. They are suitable for a wide range of …

Majority vote ensembles of conformal predictors

G Cherubin - Machine Learning, 2019 - Springer
We study majority vote ensembles of ε ε-valid conformal predictors (CP). We show that the
prediction set\varGamma^ η Γ η produced as the majority vote among the prediction …