Generalization Comparison of Deep Neural Networks via Output Sensitivity
This provides a method to compare generalization performance for deep learning practitioners, but it is incremental as it builds on existing insights without introducing a new paradigm.
The paper tackled the problem of understanding generalization in deep neural networks by linking loss function to output sensitivity to input, finding a strong empirical relation between output sensitivity and variance in bias-variance decomposition, which suggests sensitivity as a metric for comparing generalization without labeled data.
Although recent works have brought some insights into the performance improvement of techniques used in state-of-the-art deep-learning models, more work is needed to understand their generalization properties. We shed light on this matter by linking the loss function to the output's sensitivity to its input. We find a rather strong empirical relation between the output sensitivity and the variance in the bias-variance decomposition of the loss function, which hints on using sensitivity as a metric for comparing the generalization performance of networks, without requiring labeled data. We find that sensitivity is decreased by applying popular methods which improve the generalization performance of the model, such as (1) using a deep network rather than a wide one, (2) adding convolutional layers to baseline classifiers instead of adding fully-connected layers, (3) using batch normalization, dropout and max-pooling, and (4) applying parameter initialization techniques.