与马尔可夫预测策略竞争
Competing with Markov prediction strategies
摘要:
假设预测中的损失函数是凸的,我们构造了一个对这类马尔可夫预测策略通用的预测策略,它不一定是连续的。允许随机化,我们删除了凸性的要求。
英文摘要:
Assuming that the loss function is convex in the prediction, we construct a prediction strategy universal for the class of Markov prediction strategies, not necessarily continuous. Allowing randomization, we remove the requirement of convexity.
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。