基于逐次函数梯度优化的非凸模型引导学习
Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization
RJ Research Consulting（RJ研究咨询公司）；Hong Kong University of Science and Technology（香港科技大学）
摘要：
本文提出了一个连续函数梯度优化的框架，用于训练非凸模型，如神经网络，其中训练是由函数空间中的镜像下降驱动的。我们提供了一个理论分析和实证研究的培训方法，从这个框架。结果表明，该方法导致更好的性能比标准的训练技术。
英文摘要：
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.
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。
