2024-06-30-chin24a.md

abstract	section	title	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
Glauber dynamics are a natural model of dynamics of dependent systems. While originally introduced in statistical physics, they have found important applications in the study of social networks, computer vision and other domains. In this work, we introduce a model of corrupted Glauber dynamics whereby instead of updating according to the prescribed conditional probabilities, some of the vertices and their updates are controlled by an adversary. We study the effect of such corruptions on global features of the system. Among the questions we study are: How many nodes need to be controlled in order to change the average statistics of the system in polynomial time? And how many nodes are needed to obstruct approximate convergence of the dynamics? Given a specific budget, how can the adversary choose nodes to control to maximize the overall effect? Our results can be viewed as studying the robustness of classical sampling methods and are thus related to robust inference. The proofs connect to classical theory of Glauber dynamics from statistical physics.	Original Papers	The power of an adversary in Glauber dynamics	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	chin24a	0	The power of an adversary in Glauber dynamics	1102	1124	1102-1124	1102	false	Chin, Byron and Moitra, Ankur and Mossel, Elchanan and Sandon, Colin	given family Byron Chin given family Ankur Moitra given family Elchanan Mossel given family Colin Sandon	2024-06-30		Proceedings of Thirty Seventh Conference on Learning Theory	247	inproceedings	date-parts 2024 6 30	https://proceedings.mlr.press/v247/chin24a/chin24a.pdf