arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1709.06680stat.MLcs.LG
收藏

深格网络与部分单调函数

Deep Lattice Networks and Partial Monotonic Functions

Google Inc.(谷歌公司)

Seungil You, David Ding, Kevin Canini, Jan Pfeifer, Maya Gupta

摘要:

我们建议通过交替线性嵌入层、格的集合和校准器(分段线性函数)来学习深度模型,这些模型相对于用户指定的输入集是单调的,并对单调性进行适当的约束,并联合训练所得网络。我们在TensorFlow中使用新的计算图节点实现了层和投影,并使用了ADAM优化器和批量随机梯度。在基准和真实世界数据集上的实验表明,六层单调深度格型网络在单调性保证的情况下实现了最先进的分类和回归性能。

英文摘要:

We propose learning deep models that are monotonic with respect to a user-specified set of inputs by alternating layers of linear embeddings, ensembles of lattices, and calibrators (piecewise linear functions), with appropriate constraints for monotonicity, and jointly training the resulting network. We implement the layers and projections with new computational graph nodes in TensorFlow and use the ADAM optimizer and batched stochastic gradients. Experiments on benchmark and real-world datasets show that six-layer monotonic deep lattice networks achieve state-of-the art performance for classification and regression with monotonicity guarantees.

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。

↑