Poster
Guided Learning of Nonconvex Models through Successive Functional Gradient Optimization
Rie Johnson · Tong Zhang
Virtual
Keywords: [ Deep Learning - Algorithms ] [ Algorithms ] [ Optimization ]
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.