To raise or not to raise: the autonomous learning rate question

Xiaomeng Dong, Tao Tan, Michael Potter, Yun Chan Tsai, Gaurav Kumar, V.  Ratna Saripalli, Theodore Trafalis

研究成果: Article同行評審

1 引文 斯高帕斯(Scopus)

摘要

There is a parameter ubiquitous throughout the deep learning world: learning rate. There is likewise a ubiquitous question: what should that learning rate be? The true answer to this question is often tedious and time consuming to obtain, and a great deal of arcane knowledge has accumulated in recent years over how to pick and modify learning rates to achieve optimal training performance. Moreover, the long hours spent carefully crafting the perfect learning rate can come to nothing the moment your network architecture, optimizer, dataset, or initial conditions change ever so slightly. But it need not be this way. We propose a new answer to the great learning rate question: the Autonomous Learning Rate Controller. Find it at https://github.com/fastestimator/ARC/tree/v2.0.

原文English
頁(從 - 到)1679-1698
頁數20
期刊Annals of Mathematics and Artificial Intelligence
92
發行號6
DOIs
出版狀態Published - 12月 2024
對外發佈

指紋

深入研究「To raise or not to raise: the autonomous learning rate question」主題。共同形成了獨特的指紋。

引用此