# Stochastic Gradient Descent with Hyperbolic-Tangent Decay on Classification Source: [Stochastic Gradient Descent with Hyperbolic-Tangent Decay on Classification]() Collection index: [llms.txt]() Data updated: 2025-10-25T21:18:52.954Z Authors: Bo Yang Hsueh, Wei Li, I-Chen Wu Published: 2018-06-05T10:14:01.000Z ## Abstract Learning rate scheduler has been a critical issue in the deep neural network training. Several schedulers and methods have been proposed, including step decay scheduler, adaptive method, cosine scheduler and cyclical scheduler. This paper proposes a new scheduling method, named hyperbolic-tangent decay (HTD). We run experiments on several benchmarks such as: ResNet, Wide ResNet and DenseNet for CIFAR-10 and CIFAR-100 datasets, LSTM for PAMAP2 dataset, ResNet on ImageNet and Fashion-MNIST datasets. In our experiments, HTD outperforms step decay and cosine scheduler in nearly all cases, while requiring less hyperparameters than step decay, and more flexible than cosine scheduler. Code is available at https://github.com/BIGBALLON/HTD. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()