首页 | 本学科首页   官方微博 | 高级检索  
     检索      


Phase Transitions in Transfer Learning for High-Dimensional Perceptrons
Authors:Oussama Dhifallah  Yue M Lu
Institution:John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02138, USA;
Abstract:Transfer learning seeks to improve the generalization performance of a target task by exploiting the knowledge learned from a related source task. Central questions include deciding what information one should transfer and when transfer can be beneficial. The latter question is related to the so-called negative transfer phenomenon, where the transferred source information actually reduces the generalization performance of the target task. This happens when the two tasks are sufficiently dissimilar. In this paper, we present a theoretical analysis of transfer learning by studying a pair of related perceptron learning tasks. Despite the simplicity of our model, it reproduces several key phenomena observed in practice. Specifically, our asymptotic analysis reveals a phase transition from negative transfer to positive transfer as the similarity of the two tasks moves past a well-defined threshold.
Keywords:transfer learning  statistics  phase transitions
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号