arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1301.6408cs.ITmath.IT
收藏

预测单个序列的一种通用概率分配

A Universal Probability Assignment for Prediction of Individual Sequences

Yuval Lomnitz, Meir Feder

摘要:

用过去事件发生的频率作为未来事件发生频率的指南(就像我们都做的那样)是个好主意吗?在本文中,这个问题是攻击的角度普遍预测的个别序列。证明了存在一个普适的序贯概率分配,使得对于一个大类损失函数(优化目标),在此概率下使期望损失最小的预测子是一个好的普适预测子.所提出的概率分配是基于随机抖动的经验频率的状态在过去,它很容易表明,随机化是必不可少的。这产生了一个非常简单的通用预测方案,它类似于跟随扰动领导者(FPL),适用于一大类损失函数,以及使用概率假设的部分理由。

英文摘要:

Is it a good idea to use the frequency of events in the past, as a guide to their frequency in the future (as we all do anyway)? In this paper the question is attacked from the perspective of universal prediction of individual sequences. It is shown that there is a universal sequential probability assignment, such that for a large class loss functions (optimization goals), the predictor minimizing the expected loss under this probability, is a good universal predictor. The proposed probability assignment is based on randomly dithering the empirical frequencies of states in the past, and it is easy to show that randomization is essential. This yields a very simple universal prediction scheme which is similar to Follow-the-Perturbed-Leader (FPL) and works for a large class of loss functions, as well as a partial justification for using probabilistic assumptions.

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。

↑