一种新的Hedging算法及其在潜在随机变量推断中的应用
A new Hedging algorithm and its application to inferring latent random variables
摘要：
提出了一种新的累积折扣增益在线学习算法。该学习算法不对专家使用指数权重。相反，它使用的加权方案取决于主算法相对于专家的遗憾。特别是，专家的折扣累积增益小于（差）的主算法接收零权重。我们还概述了如何后悔为基础的算法可以用来作为一种替代贝叶斯平均的上下文中推断潜在的随机变量。
英文摘要：
We present a new online learning algorithm for cumulative discounted gain. This learning algorithm does not use exponential weights on the experts. Instead, it uses a weighting scheme that depends on the regret of the master algorithm relative to the experts. In particular, experts whose discounted cumulative gain is smaller (worse) than that of the master algorithm receive zero weight. We also sketch how a regret-based algorithm can be used as an alternative to Bayesian averaging in the context of inferring latent random variables.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
