To Raise or Not To Raise: The Autonomous Learning Rate Question
Abstract
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
Keywords
Cite
@article{arxiv.2106.08767,
title = {To Raise or Not To Raise: The Autonomous Learning Rate Question},
author = {Xiaomeng Dong and Tao Tan and Michael Potter and Yun-Chan Tsai and Gaurav Kumar and V. Ratna Saripalli and Theodore Trafalis},
journal= {arXiv preprint arXiv:2106.08767},
year = {2023}
}