无分布的一遍学习
Distribution-Free One-Pass Learning
摘要：
在许多大规模的机器学习应用中，数据是随着时间积累的，因此，适当的模型应该能够在线更新。此外，由于在构建模型时整个数据量是未知的，因此期望利用与数据量无关的存储器仅扫描每个数据项一次。还值得注意的是，在数据积累过程中，潜在的分布可能会发生变化。为了处理这样的任务，在本文中，我们提出了DFOP，一种无分布的单遍学习方法。当分布在数据积累期间发生变化时，这种方法工作得很好，而不需要关于变化的先验知识。每个数据项一旦被扫描就可以被丢弃。理论证明表明，在较弱的假设条件下，估计误差减小，直至以高概率收敛。实验验证了DFOP在回归和分类方面的性能。
英文摘要：
In many large-scale machine learning applications, data are accumulated with time, and thus, an appropriate model should be able to update in an online paradigm. Moreover, as the whole data volume is unknown when constructing the model, it is desired to scan each data item only once with a storage independent with the data volume. It is also noteworthy that the distribution underlying may change during the data accumulation procedure. To handle such tasks, in this paper we propose DFOP, a distribution-free one-pass learning approach. This approach works well when distribution change occurs during data accumulation, without requiring prior knowledge about the change. Every data item can be discarded once it has been scanned. Besides, theoretical guarantee shows that the estimate error, under a mild assumption, decreases until convergence with high probability. The performance of DFOP for both regression and classification are validated in experiments.
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。
