Marginal-likelihood based model-selection, even though promising, is rarely used in deep learning due to estimation difficulties. Instead, most approaches rely on validation data, which may not be readily available. In this work, we present a scalable marginal-likelihood estimation method to select both the hyperparameters and network architecture based on the training data alone. Some hyperparameters can be estimated online during training, simplifying the procedure. Our marginal-likelihood estimate is based on Laplace's method and Gauss-Newton approximations to the Hessian, and it outperforms cross-validation and manual-tuning on standard regression and image classification datasets, especially in terms of calibration and out-of-distribution detection. Our work shows that marginal likelihoods can improve generalization and be useful when validation data is unavailable (e.g., in nonstationary settings).

作为深度学习中模型选择的有前途的边际似然方法由于参数估计上的困难很少被使用。本研究提出了可伸缩的边缘似然估计方法，用于基于训练数据独立地选择超参数和网络结构。该方法建立在拉普拉斯方法和高斯牛顿逼近的黑塞矩阵的基础上，并在标准回归和图像分类数据集上表现优异。此外，该方法还能够在缺少验证数据（例如在非平稳设置中）时提高一般化性能。

深度学习模型选择的可扩展边缘似然估计