2024-09-12-an24a.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
Convergence Behavior of an Adversarial Weak Supervision Method	Labeling data via rules-of-thumb and minimal label supervision is central to Weak Supervision, a paradigm subsuming subareas of machine learning such as crowdsourced learning and semi-supervised ensemble learning. By using this labeled data to train modern machine learning methods, the cost of acquiring large amounts of hand labeled data can be ameliorated. Approaches to combining the rules-of-thumb falls into two camps, reflecting different ideologies of statistical estimation. The most common approach, exemplified by the Dawid-Skene model, is based on probabilistic modeling. The other, developed in the work of Balsubramani-Freund and others, is adversarial and game-theoretic. We provide a variety of statistical results for the adversarial approach under log-loss: we characterize the form of the solution, relate it to logistic regression, demonstrate consistency, and give rates of convergence. On the other hand, we find that probabilistic approaches for the same model class can fail to be consistent. Experimental results are provided to corroborate the theoretical results.	q9TqTSk9cy	https://github.com/stevenan5/balsubramani-freund-uai-2024	Papers	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	an24a	0	Convergence Behavior of an Adversarial Weak Supervision Method	1	49	1-49	1	false	An, Steven and Dasgupta, Sanjoy	given family Steven An given family Sanjoy Dasgupta	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/an24a/an24a.pdf