arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 0908.4494cs.ITcs.CCmath.ITmath.PR
收藏

学习、复杂性和信息密度

Learning, complexity and information density

Joel Ratsaby

摘要:

学习者的复杂性和错误的随机性之间有什么关系?这个问题提出了\cite{rat0903}谁表明,越复杂的学习者的可能性越高,他的错误偏离一个真正的随机序列。在本文中,我们报告了这个问题的实证调查。我们调查的随机性,随机性和算法的复杂性的二进制序列的错误。在由$k^{*}$阶的马尔可夫源产生的有限二进制序列上训练具有$k$阶的马尔可夫模型的学习器,并在不同的随机序列上进行测试。作为学习者复杂性的度量,我们定义了一个称为\emph{sysRatio}的量,用$ρ$表示,它是二进制字符串的压缩和未压缩长度之间的比率,其$i^{th}$位表示在学习者模型的状态$i$处做出的最大\emph{a posteriori}决策。$ρ$是信息密度的度量。本文的主要结果表明,这个比例是至关重要的回答上述问题。结果表明,存在一个临界阈值$ρ^{*}$,使得当$ρ\leqρ^{*}$时,错误序列具有以下特征:(1)\emph{} \emph{}与随机序列的低发散度$Δ$;(2)算法复杂度的低方差。当$ρ>ρ^{*}$时,错误序列的特征急剧地朝着\emph{}高\emph{$Δ$}和算法复杂度的高方差变化。

英文摘要:

What is the relationship between the complexity of a learner and the randomness of his mistakes? This question was posed in \cite{rat0903} who showed that the more complex the learner the higher the possibility that his mistakes deviate from a true random sequence. In the current paper we report on an empirical investigation of this problem. We investigate two characteristics of randomness, the stochastic and algorithmic complexity of the binary sequence of mistakes. A learner with a Markov model of order $k$ is trained on a finite binary sequence produced by a Markov source of order $k^{*}$ and is tested on a different random sequence. As a measure of learner's complexity we define a quantity called the \emph{sysRatio}, denoted by $ρ$, which is the ratio between the compressed and uncompressed lengths of the binary string whose $i^{th}$ bit represents the maximum \emph{a posteriori} decision made at state $i$ of the learner's model. The quantity $ρ$ is a measure of information density. The main result of the paper shows that this ratio is crucial in answering the above posed question. The result indicates that there is a critical threshold $ρ^{*}$ such that when $ρ\leqρ^{*}$ the sequence of mistakes possesses the following features: (1)\emph{}low divergence $Δ$ from a random sequence, (2) low variance in algorithmic complexity. When $ρ>ρ^{*}$, the characteristics of the mistake sequence changes sharply towards a\emph{}high\emph{$Δ$} and high variance in algorithmic complexity.

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。

↑