The Futility of Bias-Free Learning and Search
The Futility of Bias-Free Learning and Search
复制标题
无偏见学习和搜索的徒劳
DOI：
10.1007/978-3-030-35288-2_23
复制
发表时间：
2019
影响因子：
2.5
通讯作者：
Julia Vendemiatti
中科院分区：
文献类型：
--
作者：
George D. Montañez;J. Hayase;Julius Lauw;D. Macias;Akshay Trikha;Julia Vendemiatti
基于机器学习作为搜索的观点，我们证明了学习中偏见的必要性，量化了偏见的作用（相对于可能的数据集集合，或者更一般地说，信息资源），以增加成功的可能性。对于给定的对固定目标的偏差程度，我们证明了有利信息资源的比例从上面严格限定。此外，我们证明了偏差是一个守恒量，因此没有算法可以同时对许多不同的目标有利地偏置。因此，偏见对权衡进行了编码。任务成功的概率也可以用几何方法来衡量，即实际任务的情况与算法假设的情况之间的一致性角度，即算法的偏差。最后，在一组固定的信息资源上找到一个有利的偏置分布是很困难的，除非这组资源本身相对于给定的任务和算法已经是有利的。
Building on the view of machine learning as search, we demonstrate the necessity of bias in learning, quantifying the role of bias (measured relative to a collection of possible datasets, or more generally, information resources) in increasing the probability of success. For a given degree of bias towards a fixed target, we show that the proportion of favorable information resources is strictly bounded from above. Furthermore, we demonstrate that bias is a conserved quantity, such that no algorithm can be favorably biased towards many distinct targets simultaneously. Thus bias encodes trade-offs. The probability of success for a task can also be measured geometrically, as the angle of agreement between what holds for the actual task and what is assumed by the algorithm, represented in its bias. Lastly, finding a favorably biasing distribution over a fixed set of information resources is provably difficult, unless the set of resources itself is already favorable with respect to the given task and algorithm.