Abstract: We study the interplay between communication and feedback in a cooperative online learning setting, where a network of communicating agents learn a common sequential decision-making task through a feedback graph. We bound the network regret in terms of the independence number of the strong product between the communication network and the feedback graph. Our analysis recovers as special cases many previously known bounds for cooperative online learning with expert or bandit feedback. We also prove an instance-based lower bound, demonstrating that our positive results are not improvable except in pathological cases. Experiments on synthetic data confirm our theoretical findings.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: Implemented requested minor revisions.
Supplementary Material: pdf
Assigned Action Editor: ~Nishant_A_Mehta1
Submission Number: 1820
Loading