HOW WELL DO BAYES METHODS WORK FOR ON-LINE PREDICTION OF {+- 1} VALUES?
HOW WELL DO BAYES METHODS WORK FOR ON-LINE PREDICTION OF {+- 1} VALUES?
复制标题
贝叶斯方法对于 { - 1} 值的在线预测效果如何？
DOI：
--
复制
发表时间：
1992
期刊：
影响因子：
--
通讯作者：
A. Barron
中科院分区：
文献类型：
--
作者：
D. Haussler;A. Barron
我们研究顺序分类和回归问题，其中{+- 1}-标记的实例被在线给出，一次一个，对于每个新实例，在看到标签之前，学习系统必须预测标签，或者估计标签是+1的概率。我们来看看贝叶斯方法在这项任务中的性能，通过分类问题的错误总数和回归问题的总日志损失（或信息增益）来衡量。我们的研究结果是通过比较贝叶斯方法的性能，一个假设的“无所不知的科学家”谁是能够使用额外的信息，将无法在标准的学习协议的标签过程中的性能。结果表明，在许多情况下，贝叶斯方法的表现只比无所不知的科学家略差。这些结果推广了Haussler，Kearns和Schapire以及Opper和Haussler的结果.
We look at sequential classification and regression problems in which {+- 1}-labeled instances are given on-line, one at a time, and for each new instance, before seeing the label, the learning system must either predict the label, or estimate the probability that the label is +1. We look at the performance of Bayes method for this task, as measured by the total number of mistakes for the classification problem, and by the total log loss (or information gain) for the regression problem. Our results are given by comparing the performance of Bayes method to the performance of a hypothetical "omniscient scientist" who is able to use extra information about the labeling process that would not be available in the standard learning protocol. The results show that Bayes methods perform only slightly worse than the omniscient scientist in many cases. These results generalize previous results of Haussler, Kearns and Schapire, and Opper and Haussler.