Gravity Optimizer：一种深度学习优化的运动学方法
Gravity Optimizer: a Kinematic Approach on Optimization in Deep Learning
摘要：
我们介绍重力，另一种基于梯度的优化算法。在本文中，我们解释了我们的新想法如何改变参数以减少深度学习模型的损失。它有三个直观的超参数，为他们提出了最佳值。此外，我们还提出了一种替代移动平均线的方法。为了比较Gravity优化器与两种常见优化器Adam和RMSProp的性能，在两个VGGNet模型上训练了五个标准数据集，批量大小为128，每次100 epoch。重力超参数不需要针对不同的模型进行调整。正如将在本文中更多地解释的那样，为了研究优化器本身对损失减少的直接影响，没有使用过拟合预防技术。所获得的结果表明，重力优化器具有比亚当和RMSProp更稳定的性能，并为具有更多输出类的数据集（如CIFAR-100（精细））提供更高的验证精度值。
英文摘要：
We introduce Gravity, another algorithm for gradient-based optimization. In this paper, we explain how our novel idea change parameters to reduce the deep learning model's loss. It has three intuitive hyper-parameters that the best values for them are proposed. Also, we propose an alternative to moving average. To compare the performance of the Gravity optimizer with two common optimizers, Adam and RMSProp, five standard datasets were trained on two VGGNet models with a batch size of 128 for 100 epochs. Gravity hyper-parameters did not need to be tuned for different models. As will be explained more in the paper, to investigate the direct impact of the optimizer itself on loss reduction no overfitting prevention technique was used. The obtained results show that the Gravity optimizer has more stable performance than Adam and RMSProp and gives greater values of validation accuracy for datasets with more output classes like CIFAR-100 (Fine).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
