arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1603.06340stat.ML
收藏

基于Levy过程的数据扩充

Data Augmentation via Levy Processes

Stefan Wager, William Fithian, Percy Liang

摘要:

如果一个文档是关于旅行的,我们可能会期望文档的简短片段也应该是关于旅行的。我们介绍了一个一般的框架,将这些类型的不变性到一个判别分类。该框架将数据想象为从Levy过程的一个切片中提取。如果我们在较早的时间点对Levy过程进行切片,我们将获得额外的伪示例,这些伪示例可用于训练分类器。我们证明了该方案具有两个理想的性质:它保留了贝叶斯决策边界,并且它相当于在我们将时间倒回0的极限中拟合生成模型。我们的构造捕获了流行的方案,如高斯特征噪声和辍学训练,以及承认新的概括。

英文摘要:

If a document is about travel, we may expect that short snippets of the document should also be about travel. We introduce a general framework for incorporating these types of invariances into a discriminative classifier. The framework imagines data as being drawn from a slice of a Levy process. If we slice the Levy process at an earlier point in time, we obtain additional pseudo-examples, which can be used to train the classifier. We show that this scheme has two desirable properties: it preserves the Bayes decision boundary, and it is equivalent to fitting a generative model in the limit where we rewind time back to 0. Our construction captures popular schemes such as Gaussian feature noising and dropout training, as well as admitting new generalizations.

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。

↑