SOURCE-LINKED INTELLIGENCE

The Role of Coordinates in Pareto Regret for Adversarial Multi-Objective Bandits

arXiv · AI, language, vision and robotics · article · Sep 19, 2026 · UTC

Adversarial multi-objective bandits hold the potential to help us optimize choices (arms) whose reward is a multidimensional vector chosen by an adversary and whose performance is measured by Pareto regret. We define loss as one minus reward and measure the easiness of a coordinate by the smallest cumulative loss of the arms on it, and call the coordinate easier when this quantity is smaller. Existing work suggests that in theory an easier coordinate may reduce Pareto regret. However, in practice, one may not know which coordinate is easier. On the negative side, we show that this lack of info

Read original source ↗ Open in workspace

recordType

paper

region

Global