论文标题
较低损失反馈的专家：一个统一的框架
Experts with Lower-Bounded Loss Feedback: A Unifying Framework
论文作者
论文摘要
最佳专家问题最突出的反馈模型是完整的信息和强盗模型。在这项工作中，我们考虑了一个简单的反馈模型，该模型将这两者概括为两回合，除了强盗反馈外，对手还为每个专家的损失提供了下限。可以在各种情况下，例如在库存交易中或评估某些测量设备的错误时获得这样的小界限。对于此模型，我们证明了对EXP3的修改版本的最佳遗憾界限（超过对数因素），概括算法和bandit和全信息设置。我们的二阶统一遗憾分析模拟了两步的损失更新，并突出了三个黑森或黑森州般的表达式，这些表达式映射到了完全信息的遗憾，匪徒后悔和两者的混合体。我们的结果与带有图形结构反馈的匪徒的结果相交，因为这两种设置都可以在每个回合的专家子集中适应反馈。但是，我们的模型还可以通过允许每种损失的非平凡下限来适应单一功能水平的部分反馈。
The most prominent feedback models for the best expert problem are the full information and bandit models. In this work we consider a simple feedback model that generalizes both, where on every round, in addition to a bandit feedback, the adversary provides a lower bound on the loss of each expert. Such lower bounds may be obtained in various scenarios, for instance, in stock trading or in assessing errors of certain measurement devices. For this model we prove optimal regret bounds (up to logarithmic factors) for modified versions of Exp3, generalizing algorithms and bounds both for the bandit and the full-information settings. Our second-order unified regret analysis simulates a two-step loss update and highlights three Hessian or Hessian-like expressions, which map to the full-information regret, bandit regret, and a hybrid of both. Our results intersect with those for bandits with graph-structured feedback, in that both settings can accommodate feedback from an arbitrary subset of experts on each round. However, our model also accommodates partial feedback at the single-expert level, by allowing non-trivial lower bounds on each loss.
