Conformal Inference is (almost) Free for Neural Networks Trained with Early Stopping.

Ziyi Liang Yanfei Zhou Matteo Sesia

Published in: ICML (2023)

Keyphrases

early stopping
neural network
training process
artificial neural networks
stochastic gradient descent
bayesian networks
support vector machine
svm classifier
bayesian inference
data sets
training set
active learning
prediction accuracy
boosting algorithms