arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1504.02870stat.MLcs.LG
收藏

增量数据修改的快速敏感性分析及其在线性分类问题中的应用

Quick sensitivity analysis for incremental data modification and its application to leave-one-out CV in linear classification problems

Nagoya Institute of Technology(名古屋工业大学)

Shota Okumura, Yoshiki Suzuki, Ichiro Takeuchi

摘要:

我们介绍了一种新的敏感性分析框架,大规模的分类问题,可以使用时,少量的实例增量添加或删除。为了在这种情况下快速更新分类器,增量学习算法在文献中得到了深入研究。虽然它们比从头开始解决优化问题要有效得多,但它们的计算复杂度仍然取决于整个训练集的大小。这意味着,如果原始训练集很大,完全解决增量学习问题可能仍然相当昂贵。为了规避这个计算问题,我们提出了一个新的框架,使我们能够对更新的分类器进行推断,而无需实际重新优化它。具体来说,所提出的框架可以快速提供一个未知的更新分类器上的数量的下限和上限。所提出的框架的主要优点是,计算这些边界的计算成本只取决于更新的实例的数量。这个属性在典型的敏感性分析任务中是非常有利的,在这个任务中只有少量的实例被更新。在本文中,我们证明了所提出的框架是适用于各种实际的敏感性分析任务,框架提供的界限往往是足够紧,使所需的推论。

英文摘要:

We introduce a novel sensitivity analysis framework for large scale classification problems that can be used when a small number of instances are incrementally added or removed. For quickly updating the classifier in such a situation, incremental learning algorithms have been intensively studied in the literature. Although they are much more efficient than solving the optimization problem from scratch, their computational complexity yet depends on the entire training set size. It means that, if the original training set is large, completely solving an incremental learning problem might be still rather expensive. To circumvent this computational issue, we propose a novel framework that allows us to make an inference about the updated classifier without actually re-optimizing it. Specifically, the proposed framework can quickly provide a lower and an upper bounds of a quantity on the unknown updated classifier. The main advantage of the proposed framework is that the computational cost of computing these bounds depends only on the number of updated instances. This property is quite advantageous in a typical sensitivity analysis task where only a small number of instances are updated. In this paper we demonstrate that the proposed framework is applicable to various practical sensitivity analysis tasks, and the bounds provided by the framework are often sufficiently tight for making desired inferences.

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。

↑