Fractal Dimension Generalization Measure
This paper addresses the problem of robustly measuring generalization performance for machine learning models, which is important for practitioners and researchers in the field.
This paper proposes a generalization measure for machine learning models based on the fractal dimension of their decision boundaries. It was developed as part of the "Predicting Generalization in Deep Learning" competition.
Developing a robust generalization measure for the performance of machine learning models is an important and challenging task. A lot of recent research in the area focuses on the model decision boundary when predicting generalization. In this paper, as part of the "Predicting Generalization in Deep Learning" competition, we analyse the complexity of decision boundaries using the concept of fractal dimension and develop a generalization measure based on that technique.