The weighted majority algorithm
Information and Computation
Collaboration of untrusting peers with changing interests
EC '04 Proceedings of the 5th ACM conference on Electronic commerce
Adaptive Collaboration in Peer-to-Peer Systems
ICDCS '05 Proceedings of the 25th IEEE International Conference on Distributed Computing Systems
Improved recommendation systems
SODA '05 Proceedings of the sixteenth annual ACM-SIAM symposium on Discrete algorithms
Collaborate with strangers to find own preferences
Proceedings of the seventeenth annual ACM symposium on Parallelism in algorithms and architectures
Tell me who I am: an interactive recommendation system
Proceedings of the eighteenth annual ACM symposium on Parallelism in algorithms and architectures
Towards a scalable and robust DHT
Proceedings of the eighteenth annual ACM symposium on Parallelism in algorithms and architectures
Robust random number generation for peer-to-peer systems
OPODIS'06 Proceedings of the 10th international conference on Principles of Distributed Systems
Competitive collaborative learning
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Robust distributed name service
IPTPS'04 Proceedings of the Third international conference on Peer-to-Peer Systems
Distributed weighted stable marriage problem
SIROCCO'10 Proceedings of the 17th international conference on Structural Information and Communication Complexity
Hi-index | 0.00 |
We consider a model for sequential online decision-making by many diverse agents. On each day, each agent makes a decision, and pays a penalty if it is a mistake. Obviously, it would be good for agents to avoid repeating the same mistakes made by other agents; however, difficulty may arise when some agents disagree over what constitutes a mistake, perhaps maliciously. As a metric of success for this problem, we consider dynamic regret, i.e., regret versus the off-line optimal sequence of decisions. Previous regret bounds usually use the much weaker notion of static regret, i.e., regret versus the best single decision in hindsight. We assume there is a set of "honest" players whose valuations for the decisions at each time step are identical. No assumptions are made about the remaining players, and the algorithm assumes no information about which are the honest players. We present an algorithm for this setting whose expected dynamic regret per honest player is optimal up to a multiplicative constant and an additive polylogarithmic term, assuming the number of options is bounded.