Conformalized Credal Set Predictors
CoRR(2024)
摘要
Credal sets are sets of probability distributions that are considered as
candidates for an imprecisely known ground-truth distribution. In machine
learning, they have recently attracted attention as an appealing formalism for
uncertainty representation, in particular due to their ability to represent
both the aleatoric and epistemic uncertainty in a prediction. However, the
design of methods for learning credal set predictors remains a challenging
problem. In this paper, we make use of conformal prediction for this purpose.
More specifically, we propose a method for predicting credal sets in the
classification task, given training data labeled by probability distributions.
Since our method inherits the coverage guarantees of conformal prediction, our
conformal credal sets are guaranteed to be valid with high probability (without
any assumptions on model or distribution). We demonstrate the applicability of
our method to natural language inference, a highly ambiguous natural language
task where it is common to obtain multiple annotations per example.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要