论文标题
通过腐败的专家建议进行预测
Prediction with Corrupted Expert Advice
论文作者
论文摘要
在环境是良性并随机造成损失的环境中，我们重新审视了预测的基本问题，但是学习者观察到的反馈是要遭受适度的对抗性腐败。我们证明，经典乘法权重算法的变体随着步骤尺寸的减小，在这种情况下会持续遗憾，并且在各种环境中都可以在各种环境中进行最佳性能，无论注射损坏的幅度如何。我们的结果表明，经常可比的正规领导者（FTRL）和在线镜下降（OMD）框架之间存在令人惊讶的差异：我们表明，对于损坏的随机制度专家而言，OMD的遗憾实际上与FTRL的遗憾相差。
We revisit the fundamental problem of prediction with expert advice, in a setting where the environment is benign and generates losses stochastically, but the feedback observed by the learner is subject to a moderate adversarial corruption. We prove that a variant of the classical Multiplicative Weights algorithm with decreasing step sizes achieves constant regret in this setting and performs optimally in a wide range of environments, regardless of the magnitude of the injected corruption. Our results reveal a surprising disparity between the often comparable Follow the Regularized Leader (FTRL) and Online Mirror Descent (OMD) frameworks: we show that for experts in the corrupted stochastic regime, the regret performance of OMD is in fact strictly inferior to that of FTRL.
