Optimizing Data Augmentation through Bayesian Model Selection
This work addresses the challenge of selecting data augmentation strategies for machine learning practitioners, offering a more systematic approach, though it is incremental as it builds on existing Bayesian methods.
The paper tackled the problem of optimizing data augmentation parameters, which is typically done through trial-and-error, by proposing a Bayesian model selection framework that optimizes these parameters via a tractable ELBO, resulting in improved calibration and robust performance in computer vision tasks.
Data Augmentation (DA) has become an essential tool to improve robustness and generalization of modern machine learning. However, when deciding on DA strategies it is critical to choose parameters carefully, and this can be a daunting task which is traditionally left to trial-and-error or expensive optimization based on validation performance. In this paper, we counter these limitations by proposing a novel framework for optimizing DA. In particular, we take a probabilistic view of DA, which leads to the interpretation of augmentation parameters as model (hyper)-parameters, and the optimization of the marginal likelihood with respect to these parameters as a Bayesian model selection problem. Due to its intractability, we derive a tractable Evidence Lower BOund (ELBO), which allows us to optimize augmentation parameters jointly with model parameters. We provide extensive theoretical results on variational approximation quality, generalization guarantees, invariance properties, and connections to empirical Bayes. Through experiments on computer vision tasks, we show that our approach improves calibration and yields robust performance over fixed or no augmentation. Our work provides a rigorous foundation for optimizing DA through Bayesian principles with significant potential for robust machine learning.