arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1712.00527cs.LG
收藏

基于核采样的自适应采样Softmax

Adaptive Sampled Softmax with Kernel Based Sampling

Google(谷歌)

Guy Blanc, Steffen Rendle

摘要:

Softmax是多类问题最常用的输出函数,广泛应用于视觉、自然语言处理和推荐等领域。softmax模型在类的数量上具有线性成本,这使得它对于许多现实世界的问题来说过于昂贵。加快训练速度的一种常见方法是在每个训练步骤中只对一些类进行采样。已知该方法是有偏的,并且采样分布偏离输出分布越多,偏置就越大。然而,几乎所有最近的工作都使用简单的抽样分布,需要大样本量来减轻偏差。在这项工作中,我们提出了一类新的基于核的采样方法,并开发了一个有效的采样算法。基于核的采样在训练模型时适应模型,从而产生低偏差。基于核的采样可以很容易地应用于许多模型,因为它只依赖于模型的最后一个隐藏层。我们实证研究了偏差,抽样分布和样本大小的权衡,并表明基于核的抽样结果在低偏差与少量样本。

英文摘要:

Softmax is the most commonly used output function for multiclass problems and is widely used in areas such as vision, natural language processing, and recommendation. A softmax model has linear costs in the number of classes which makes it too expensive for many real-world problems. A common approach to speed up training involves sampling only some of the classes at each training step. It is known that this method is biased and that the bias increases the more the sampling distribution deviates from the output distribution. Nevertheless, almost any recent work uses simple sampling distributions that require a large sample size to mitigate the bias. In this work, we propose a new class of kernel based sampling methods and develop an efficient sampling algorithm. Kernel based sampling adapts to the model as it is trained, thus resulting in low bias. Kernel based sampling can be easily applied to many models because it relies only on the model's last hidden layer. We empirically study the trade-off of bias, sampling distribution and sample size and show that kernel based sampling results in low bias with few samples.

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。

↑