属性有效的学习算法
Toward Attribute Efficient Learning Algorithms
摘要:
我们在两个重要的问题上取得了进展属性有效的可学习性。首先,我们给出了一个算法学习决策表的长度$k$在$n$变量使用$2^{\tilde{O}(k^{1/3})} \log n$的例子和时间$n^{\tilde{O}(k^{1/3})}$。这是第一个学习决策表的算法,在相关参数中具有亚指数样本复杂度和亚指数运行时间。我们的方法建立了属性有效学习和多项式阈值函数之间的关系,是基于一个新的建设低程度,低权重的决策列表多项式阈值函数。对于广泛的参数,我们的建设匹配1994年的下限由于Beigel的ODDMAXBIT谓词,并给出了一个基本上最佳的多项式阈值函数度和权重之间的权衡。其次,我们使用$n$中的时间多项式中的$O(n^{1-1/k})$示例,给出了从$n$变量中学习$k$上的未知奇偶函数的算法。对于$k=o(\log n)$,这产生具有样本复杂度$o(n)$的多项式时间算法。这是第一个多项式时间算法学习奇偶性的超常数数量的变量与次线性样本复杂度。
英文摘要:
We make progress on two important problems regarding attribute efficient learnability. First, we give an algorithm for learning decision lists of length $k$ over $n$ variables using $2^{\tilde{O}(k^{1/3})} \log n$ examples and time $n^{\tilde{O}(k^{1/3})}$. This is the first algorithm for learning decision lists that has both subexponential sample complexity and subexponential running time in the relevant parameters. Our approach establishes a relationship between attribute efficient learning and polynomial threshold functions and is based on a new construction of low degree, low weight polynomial threshold functions for decision lists. For a wide range of parameters our construction matches a 1994 lower bound due to Beigel for the ODDMAXBIT predicate and gives an essentially optimal tradeoff between polynomial threshold function degree and weight. Second, we give an algorithm for learning an unknown parity function on $k$ out of $n$ variables using $O(n^{1-1/k})$ examples in time polynomial in $n$. For $k=o(\log n)$ this yields a polynomial time algorithm with sample complexity $o(n)$. This is the first polynomial time algorithm for learning parity on a superconstant number of variables with sublinear sample 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。