AI RESEARCH
Online Minimization of Polarization and Disagreement via Low-Rank Matrix Bandits
arXiv CS.LG
•
ArXi:2510.00803v2 Announce Type: replace We study the problem of minimizing polarization and disagreement in the Friedkin-Johnsen opinion dynamics model under incomplete information. Unlike prior work that assumes a static setting with full knowledge of agents' innate opinions, we address the realistic online setting where innate opinions are unknown and must be learned through sequential observations.