arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv cs/0508127cs.ITmath.IT
收藏

单个序列的上下文树预测

On context-tree prediction of individual sequences

Jacob Ziv, Neri Merhav

摘要:

基于上下文树的方法在无损数据压缩中取得了明显的成功,在本文中,我们探索了在个体序列的通用预测中具有相同精神的方法。通过上下文树预测,我们指的是一系列预测方案,其中在每个时刻$t$,在已经观察到数据序列$x_1,...,x_{t-1}$的所有结果但还没有观察到$x_t$之后,预测基于"上下文“由$k$最近的过去结果$x_{t-k},...,x_{t-1}$组成,其中$k$的选择可以取决于可能更长,虽然有限,但观察到的过去的一部分,$x_{t-k_{\max}},...x_{t-1}$。这与[1]中报道的研究不同,在[1]中,一般有限状态预测器以及固定阶的“马尔可夫”(有限记忆)预测器在单个序列的情况下进行了研究。本研究与[1]的另一个重要区别是渐近机制。而在[1]中,预测器的资源(即,状态的数量或存储器大小)保持固定而不管数据序列的长度$N$如何,这里我们研究允许上下文或状态的数量与$N$同时增长的情况。我们主要感兴趣的是以下基本问题:什么是临界增长率的情况下,最好的上下文树预测器的性能仍然是普遍可实现的,但高于它是不是?我们证明了这个临界增长率在$N$中是线性的。特别是,我们提出了一个通用的上下文树算法,基本上达到最佳性能,只要增长率是次线性的,并表明,另一方面,这是不可能的线性情况下。

英文摘要:

Motivated by the evident success of context-tree based methods in lossless data compression, we explore, in this paper, methods of the same spirit in universal prediction of individual sequences. By context-tree prediction, we refer to a family of prediction schemes, where at each time instant $t$, after having observed all outcomes of the data sequence $x_1,...,x_{t-1}$, but not yet $x_t$, the prediction is based on a ``context'' (or a state) that consists of the $k$ most recent past outcomes $x_{t-k},...,x_{t-1}$, where the choice of $k$ may depend on the contents of a possibly longer, though limited, portion of the observed past, $x_{t-k_{\max}},...x_{t-1}$. This is different from the study reported in [1], where general finite-state predictors as well as ``Markov'' (finite-memory) predictors of fixed order, were studied in the regime of individual sequences. Another important difference between this study and [1] is the asymptotic regime. While in [1], the resources of the predictor (i.e., the number of states or the memory size) were kept fixed regardless of the length $N$ of the data sequence, here we investigate situations where the number of contexts or states is allowed to grow concurrently with $N$. We are primarily interested in the following fundamental question: What is the critical growth rate of the number of contexts, below which the performance of the best context-tree predictor is still universally achievable, but above which it is not? We show that this critical growth rate is linear in $N$. In particular, we propose a universal context-tree algorithm that essentially achieves optimum performance as long as the growth rate is sublinear, and show that, on the other hand, this is impossible in the linear case.

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。

↑