Memorization in Deep Neural Networks: Does the Loss Function matter?

Abstract

Deep Neural Networks, often owing to the overparameterization, are shown to be capable of exactly memorizing even randomly labelled data. Empirical studies have also shown that none of the standard regularization techniques mitigate such overfitting. We investigate whether the choice of the loss function can affect this memorization. We empirically show, with benchmark data sets MNIST and CIFAR-10, that a symmetric loss function, as opposed to either cross-entropy or squared error loss, results in significant improvement in the ability of the network to resist such overfitting. We then provide a formal definition for robustness to memorization and provide a theoretical explanation as to why the symmetric losses provide this robustness. Our results clearly bring out the role loss functions alone can play in this phenomenon of memorization.

arXiv commentAccepted at PAKDD 2021. 12 pages and 5 figures

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• Noise Tolerance under Risk Minimization
• StructBERT: Incorporating Language Structures into Pre-training for Deep Language Understanding
• Evaluation of Neural Architectures Trained with Square Loss vs Cross-Entropy in Classification Tasks
• Classification vs regression in overparameterized regimes: Does the loss function matter?
• Neural Network Memorization Dissection