2024-09-12-jazbec24a.md

title	abstract	openreview	software	section	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Early-Exit Neural Networks with Nested Prediction Sets	Early-exit neural networks (EENNs) facilitate adaptive inference by producing predictions at multiple stages of the forward pass. In safety-critical applications, these predictions are only meaningful when complemented with reliable uncertainty estimates. Yet, due to their sequential structure, an EENN’s uncertainty estimates should also be *consistent*: labels that are deemed improbable at one exit should not reappear within the confidence interval / set of later exits. We show that standard uncertainty quantification techniques, like Bayesian methods or conformal prediction, can lead to inconsistency across exits. We address this problem by applying anytime-valid confidence sequences (AVCSs) to the exits of EENNs. By design, AVCSs maintain consistency across exits. We examine the theoretical and practical challenges of applying AVCSs to EENNs and empirically validate our approach on both regression and classification tasks.	mAjIKFHa2P	https://github.com/metodj/EENN-AVCS	Papers	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	jazbec24a	0	Early-Exit Neural Networks with Nested Prediction Sets	1780	1796	1780-1796	1780	false	Jazbec, Metod and Forr\'e, Patrick and Mandt, Stephan and Zhang, Dan and Nalisnick, Eric	given family Metod Jazbec given family Patrick Forré given family Stephan Mandt given family Dan Zhang given family Eric Nalisnick	2024-09-12		Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence	244	inproceedings	date-parts 2024 9 12	https://raw.githubusercontent.com/mlresearch/v244/main/assets/jazbec24a/jazbec24a.pdf