论文标题
通过连续的功能梯度优化对非凸模型进行指导学习
Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization
论文作者
论文摘要
本文为训练非凸模型（例如神经网络）提供了连续的功能梯度优化框架，在该模型中，训练是由功能空间中的镜下下降驱动的。我们提供了从该框架得出的训练方法的理论分析和实证研究。结果表明，该方法比标准训练技术的性能更好。
This paper presents a framework of successive functional gradient optimization for training nonconvex models such as neural networks, where training is driven by mirror descent in a function space. We provide a theoretical analysis and empirical study of the training method derived from this framework. It is shown that the method leads to better performance than that of standard training techniques.
