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.

中文翻译：

---

通过连续函数梯度优化引导学习非凸模型

本文提出了一种用于训练非凸模型（如神经网络）的连续函数梯度优化框架，其中训练由函数空间中的镜像下降驱动。我们对源自该框架的训练方法进行了理论分析和实证研究。结果表明，该方法比标准训练技术具有更好的性能。