Towards Costless Model Selection in Contextual Bandits: A Bias-Variance Perspective
迈向上下文老虎机中的无额外代价模型选择:偏差与方差视角
Model selection in supervised learning provides costless guarantees as if the model that best balances bias and variance was known a priori. We study the feasibility of similar guarantees for cumulative regret minimization in the stochastic contextual bandit setting. Recent work [Marinov and Zimmert, 2021] identifies instances where no algorithm can guarantee costless regret bounds. Nevertheless, we identify benign conditions where costless model selection is feasible:…