Phase Transitions in Transfer Learning for High-Dimensional Perceptrons.
Phase Transitions in Transfer Learning for High-Dimensional Perceptrons.
复制标题
DOI:
10.3390/e23040400
复制
发表时间:
2021-03-27
期刊:
影响因子:
--
通讯作者:
Lu YM
中科院分区:
文献类型:
--
作者:
Dhifallah O;Lu YM
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.
登录
查看更多内容
DOI:
10.1007/978-3-540-45167-9_41
发表时间:
2003-01-01
期刊:
LEARNING THEORY AND KERNEL MACHINES
影响因子:
--
作者:
Ben-David, S;Schuller, R
通讯作者:
Schuller, R
影响因子:
4.5
作者:
ANDERSEN, PK;GILL, RD
通讯作者:
GILL, RD
影响因子:
2.5
作者:
Debbah, M;Hachem, W;de Courville, M
通讯作者:
de Courville, M
影响因子:
8.9
作者:
Pan, Sinno Jialin;Yang, Qiang
通讯作者:
Yang, Qiang
影响因子:
6
作者:
Bakker, B;Heskes, T
通讯作者:
Heskes, T