arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1304.7576cs.LG
收藏

对抗性预测中的分形结构

Fractal structures in Adversarial Prediction

Microsoft Corp.(微软公司);New York University(纽约大学);University of Chicago(芝加哥大学)

Rina Panigrahy, Preyas Popat

摘要:

分形是自相似的递归结构,已被用于模拟几个现实世界的过程。在这项工作中,我们研究如何“分形”的过程中出现的预测游戏,对手正在生成一个序列的位和算法试图预测它们。我们将看到,在算法的预测收益的某种形式化下,对手产生一个类似分形的序列以最小化算法的预测能力是最优的。事实上,以前就有人提出金融市场表现出类似分形的行为。我们证明了一个分形分布自然产生的优化从对手的角度来看。此外,我们给出了可预测性和预期偏差(即位的总和)之间的最佳权衡,我们的形式化的预测回报。这一结果的动机是观察到,几个时间序列数据表现出更高的偏差比预期的完全随机游走。

英文摘要:

Fractals are self-similar recursive structures that have been used in modeling several real world processes. In this work we study how "fractal-like" processes arise in a prediction game where an adversary is generating a sequence of bits and an algorithm is trying to predict them. We will see that under a certain formalization of the predictive payoff for the algorithm it is most optimal for the adversary to produce a fractal-like sequence to minimize the algorithm's ability to predict. Indeed it has been suggested before that financial markets exhibit a fractal-like behavior. We prove that a fractal-like distribution arises naturally out of an optimization from the adversary's perspective. In addition, we give optimal trade-offs between predictability and expected deviation (i.e. sum of bits) for our formalization of predictive payoff. This result is motivated by the observation that several time series data exhibit higher deviations than expected for a completely random walk.

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。

↑