Tag: ftpl

Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems arXiv:2508.18604v1 Announce Type: new Abstract: Follow-the-Regularized-Leader (FTRL) policies have achieved Best-of-Both-Worlds (BOBW) results in various settings through hybrid regularizers, whereas analogous results for Follow-the-Perturbed-Leader (FTPL) remain limited due to inherent analytical challenges. To advance the analytical foundations of FTPL, we revisit classical FTRL-FTPL duality for unbounded perturbations…