Accelerating Feature Conformal Prediction via Taylor Approximation

Zihao Tang, Boyuan Wang, Chuan Wen, Jiaye Teng

Keywords: conformal prediction, Taylor, fast, feature, uncertainty, deep learning, representation

TL;DR: A fast version for feature conformal prediction.

Abstract:

Conformal prediction is widely adopted in uncertainty quantification, due to its post-hoc, distribution-free, and model-agnostic properties.
In the realm of modern deep learning, researchers have proposed Feature Conformal Prediction (FCP), which deploys conformal prediction in a feature space, yielding reduced band lengths.
However, the practical utility of FCP is limited due to the time-consuming non-linear operations required to transform confidence bands from feature space to output space.
In this paper, we present Fast Feature Conformal Prediction (FFCP), a method that accelerates FCP by leveraging a first-order Taylor expansion to approximate these non-linear operations.
The proposed FFCP introduces a novel non-conformity score that is both effective and efficient for real-world applications.
Empirical validations showcase that FFCP performs comparably with FCP (both outperforming the vanilla version) while achieving a significant reduction in computational time by approximately 50x in both regression and classification tasks.

Primary Area: Probabilistic methods (e.g., variational inference, causal inference, Gaussian processes)

Submission Number: 12273