2024-09-12-heuillet24a.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
Neural Active Learning Meets the Partial Monitoring Framework	We focus on the online-based active learning (OAL) setting where an agent operates over a stream of observations and trades-off between the costly acquisition of information (labelled observations) and the cost of prediction errors. We propose a novel foundation for OAL tasks based on partial monitoring, a theoretical framework specialized in online learning from partially informative actions. We show that previously studied binary and multi-class OAL tasks are instances of partial monitoring. We expand the real-world potential of OAL by introducing a new class of cost-sensitive OAL tasks. We propose NeuralCBP, the first PM strategy that accounts for predictive uncertainty with deep neural networks. Our extensive empirical evaluation on open source datasets shows that NeuralCBP has competitive performance against state-of-the-art baselines on multiple binary, multi-class and cost-sensitive OAL tasks.	K99ZSDvGiD	https://github.com/MaxHeuillet/neuralCBPside	Papers	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	heuillet24a	0	Neural Active Learning Meets the Partial Monitoring Framework	1621	1639	1621-1639	1621	false	Heuillet, Maxime and Ahmad, Ola and Durand, Audrey	given family Maxime Heuillet given family Ola Ahmad given family Audrey Durand	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/heuillet24a/heuillet24a.pdf