arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1003.0034cs.AIcs.LG
收藏

通过无悔学习对预测市场的新认识

A New Understanding of Prediction Markets Via No-Regret Learning

Harvard University(哈佛大学)

Yiling Chen, Jennifer Wortman Vaughan

摘要:

我们探索了市场评分规则、基于成本函数的预测市场和无悔学习之间存在的惊人数学联系。我们表明,任何成本函数为基础的预测市场可以解释为一个算法,通常研究的问题,从专家的意见,通过等同的行业在市场上观察到的损失的学习算法的学习。如果市场组织者的损失是有界的,这个界可以用来导出相应的学习算法的O(sqrt(T))后悔界。然后,我们表明,类的市场与凸成本函数完全对应的类的跟随正规化领导学习算法,在市场中的成本函数的选择对应的学习问题中的正则化的选择。最后,我们证明了市场评分规则和凸成本函数预测市场之间的等价性。这意味着市场评分规则也可以自然地解释为遵循正则化领导者算法,并且可能是独立的兴趣。这些联系为我们提供了新的视角,让我们了解通常研究的市场(如对数市场评分规则)如何将观点汇总为对未来事件可能性的准确估计。

英文摘要:

We explore the striking mathematical connections that exist between market scoring rules, cost function based prediction markets, and no-regret learning. We show that any cost function based prediction market can be interpreted as an algorithm for the commonly studied problem of learning from expert advice by equating trades made in the market with losses observed by the learning algorithm. If the loss of the market organizer is bounded, this bound can be used to derive an O(sqrt(T)) regret bound for the corresponding learning algorithm. We then show that the class of markets with convex cost functions exactly corresponds to the class of Follow the Regularized Leader learning algorithms, with the choice of a cost function in the market corresponding to the choice of a regularizer in the learning problem. Finally, we show an equivalence between market scoring rules and prediction markets with convex cost functions. This implies that market scoring rules can also be interpreted naturally as Follow the Regularized Leader algorithms, and may be of independent interest. These connections provide new insight into how it is that commonly studied markets, such as the Logarithmic Market Scoring Rule, can aggregate opinions into accurate estimates of the likelihood of future events.

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。

↑