Robustness to Augmentations as a Generalization metric
This work addresses the challenge of estimating generalization performance for machine learning practitioners, but it is incremental as it builds on existing ideas of using augmentations.
The authors tackled the problem of predicting model generalization by proposing a metric based on robustness to input augmentations, achieving second place in the NeurIPS competition on Predicting Generalization in Deep Learning.
Generalization is the ability of a model to predict on unseen domains and is a fundamental task in machine learning. Several generalization bounds, both theoretical and empirical have been proposed but they do not provide tight bounds .In this work, we propose a simple yet effective method to predict the generalization performance of a model by using the concept that models that are robust to augmentations are more generalizable than those which are not. We experiment with several augmentations and composition of augmentations to check the generalization capacity of a model. We also provide a detailed motivation behind the proposed method. The proposed generalization metric is calculated based on the change in the output of the model after augmenting the input. The proposed method was the first runner up solution for the NeurIPS competition on Predicting Generalization in Deep Learning.