论文标题
辍学：明确的表格和容量控制
Dropout: Explicit Forms and Capacity Control
论文作者
论文摘要
我们研究了各种机器学习问题中辍学提供的容量控制。首先，我们研究了矩阵完成的辍学，它诱导了数据依赖性的正规化器，该调整器在预期的情况下等于因子乘积的加权痕迹。在深度学习中，我们表明，由于辍学引起的数据依赖性正常化程序直接控制着深层神经网络基础类别的rademacher复杂性。这些发展使我们能够在矩阵完成和训练深神经网络中为辍学算法提供具体的概括误差界。我们评估了包括Movielens，Mnist和Fashion-Mnist在内的实际数据集的理论发现。
We investigate the capacity control provided by dropout in various machine learning problems. First, we study dropout for matrix completion, where it induces a data-dependent regularizer that, in expectation, equals the weighted trace-norm of the product of the factors. In deep learning, we show that the data-dependent regularizer due to dropout directly controls the Rademacher complexity of the underlying class of deep neural networks. These developments enable us to give concrete generalization error bounds for the dropout algorithm in both matrix completion as well as training deep neural networks. We evaluate our theoretical findings on real-world datasets, including MovieLens, MNIST, and Fashion-MNIST.
