Clipping the gradient is a known approach to improving gradient descent, but requires hand selection of a clipping threshold hyperparameter. We present AutoClip, a simple method for automatically and adaptively choosing a gradient clipping threshold, based on the history of gradient norms observed during training. Experimental results show that applying AutoClip results in improved generalization performance for audio source separation networks. Observation of the training dynamics of a separation network trained with and without AutoClip show that AutoClip guides optimization into smoother parts of the loss landscape. AutoClip is very simple to implement and can be integrated readily into a variety of applications across multiple domains.
翻译:缩放梯度是改善梯度下降的已知方法,但需要手工选择剪切阈值超参数。我们介绍AutoClip,这是一个根据培训期间所观察到的梯度规范历史自动和适应性选择梯度剪切阈值的简单方法。实验结果显示,应用AutoClip可以改善音源分离网络的概括性性能。观察经过培训的、不经过AutoClip的分离网络的培训动态显示,AutoClip引导优化到损失场景中更平滑的部分。AutoClip非常简单,可以执行,可以很容易地融入多个领域的各种应用中。