arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1403.6863cs.LG
收藏

k-CNF布尔函数的在线学习

Online Learning of k-CNF Boolean Functions

DeepMind Technologies Ltd(深度思维科技有限公司);University of Alberta(阿尔伯塔大学);Australian National University(澳大利亚国立大学)

Joel Veness, Marcus Hutter

摘要:

在对数损失下的在线学习背景下,重新讨论了从例子中学习k-CNF布尔函数的问题.在这样做的时候,我们给一个贝叶斯解释的Valiant的著名的PAC学习算法,然后我们建立在两个高效的,在线的,概率的,监督学习算法预测输出的一个未知的k-CNF布尔函数。我们分析了我们的方法的损失,并表明,累积对数损失可以上界,忽略对数因子,由每个例子的大小的多项式函数。

英文摘要:

This paper revisits the problem of learning a k-CNF Boolean function from examples in the context of online learning under the logarithmic loss. In doing so, we give a Bayesian interpretation to one of Valiant's celebrated PAC learning algorithms, which we then build upon to derive two efficient, online, probabilistic, supervised learning algorithms for predicting the output of an unknown k-CNF Boolean function. We analyze the loss of our methods, and show that the cumulative log-loss can be upper bounded, ignoring logarithmic factors, by a polynomial function of the size of each example.

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。

↑