Revisiting lp-constrained Softmax Loss: A Comprehensive Study
This work addresses the lack of a comprehensive study on normalization effects for machine learning practitioners, though it is incremental as it revisits and extends existing methods.
The paper investigates lp-constrained softmax loss classifiers across various norm orders, magnitudes, and data dimensions, finding that they achieve more accurate classification results and are less prone to overfitting in image classification tasks.
Normalization is a vital process for any machine learning task as it controls the properties of data and affects model performance at large. The impact of particular forms of normalization, however, has so far been investigated in limited domain-specific classification tasks and not in a general fashion. Motivated by the lack of such a comprehensive study, in this paper we investigate the performance of lp-constrained softmax loss classifiers across different norm orders, magnitudes, and data dimensions in both proof-of-concept classification problems and real-world popular image classification tasks. Experimental results suggest collectively that lp-constrained softmax loss classifiers not only can achieve more accurate classification results but, at the same time, appear to be less prone to overfitting. The core findings hold across the three popular deep learning architectures tested and eight datasets examined, and suggest that lp normalization is a recommended data representation practice for image classification in terms of performance and convergence, and against overfitting.