Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making

arXiv:2302.05430v2 Announce Type: replace-cross
Abstract: Smoothed online learning has emerged as a popular framework to mitigate the substantial loss in statistical and computational complexity that arises when one moves from classical to adversarial learning. Unfortunately, for some spaces, it has been shown that efficient algorithms suffer an exponentially worse regret than that which is minimax optimal, even when the learner has access to an optimization oracle over the space. To mitigate that exponential dependence, this work introduces a new notion …

abstract adversarial adversarial learning algorithms arxiv complexity computational continuous cs.lg decision decision making framework loss making online learning oracle popular spaces statistical stat.ml type