Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

Predictive Inference with Feature Conformal Prediction

Jiaye Teng · Chuan Wen · Dinghuai Zhang · Yoshua Bengio · Yang Gao · Yang Yuan

MH1-2-3-4 #21

Keywords: [ uncertainty ] [ conformal prediction ] [ Deep Learning and representational learning ]


Abstract:

Conformal prediction is a distribution-free technique for establishing valid prediction intervals. Although conventionally people conduct conformal prediction in the output space, this is not the only possibility. In this paper, we propose feature conformal prediction, which extends the scope of conformal prediction to semantic feature spaces by leveraging the inductive bias of deep representation learning. From a theoretical perspective, we demonstrate that feature conformal prediction provably outperforms regular conformal prediction under mild assumptions. Our approach could be combined with not only vanilla conformal prediction, but also other adaptive conformal prediction methods. Apart from experiments on existing predictive inference benchmarks, we also demonstrate the state-of-the-art performance of the proposed methods on \textit{large-scale} tasks such as ImageNet classification and Cityscapes image segmentation.

Chat is not available.