🏢 Alan Turing Institute

Strategic agents gaming recommender systems is solved by a novel mechanism that incentivizes truthful behavior while minimizing regret, offering a solution to a key challenge in online learning.

Algorithm RESET achieves optimal switching regret simultaneously across all segmentations, offering efficiency and parameter-free operation.

The Confidence-Rated Bandits with Abstentions (CBA) algorithm significantly improves reward bounds for prediction with expert advice by strategically leveraging an abstention action.