arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1508.01596stat.MLcs.LG
收藏

次线性分割估计

Sublinear Partition Estimation

Johns Hopkins University(约翰斯·霍普金斯大学)

Pushpendre Rastogi, Benjamin Van Durme

摘要:

神经网络分类器的输出分数通过对所有竞争类别的分数进行归一化来转换为概率。计算这个分区函数$Z$在类别数量上是线性的,这是有问题的,因为现实世界的问题集在类别类型上继续增长,例如在视觉对象识别或判别语言建模中。我们提出了三种方法的分区函数的次线性估计,基于近似最近邻搜索和核特征映射,并比较所提出的方法的性能经验。

英文摘要:

The output scores of a neural network classifier are converted to probabilities via normalizing over the scores of all competing categories. Computing this partition function, $Z$, is then linear in the number of categories, which is problematic as real-world problem sets continue to grow in categorical types, such as in visual object recognition or discriminative language modeling. We propose three approaches for sublinear estimation of the partition function, based on approximate nearest neighbor search and kernel feature maps and compare the performance of the proposed approaches empirically.

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。

↑