English

Forget the Learning Rate, Decay Loss

Machine Learning 2019-05-02 v1

Abstract

In the usual deep neural network optimization process, the learning rate is the most important hyper parameter, which greatly affects the final convergence effect. The purpose of learning rate is to control the stepsize and gradually reduce the impact of noise on the network. In this paper, we will use a fixed learning rate with method of decaying loss to control the magnitude of the update. We used Image classification, Semantic segmentation, and GANs to verify this method. Experiments show that the loss decay strategy can greatly improve the performance of the model

Keywords

Cite

@article{arxiv.1905.00094,
  title  = {Forget the Learning Rate, Decay Loss},
  author = {Jiakai Wei},
  journal= {arXiv preprint arXiv:1905.00094},
  year   = {2019}
}

Comments

Asia Conference on Machine Learning and Computing. arXiv admin note: text overlap with arXiv:1703.04782, arXiv:1611.07004 by other authors

R2 v1 2026-06-23T08:53:51.688Z