Implicit Regularization of Stochastic Gradient Descent in Natural Language Processing: Observations and Implications

Abstract

Deep neural networks with remarkably strong generalization performances are usually over-parameterized. Despite explicit regularization strategies are used for practitioners to avoid over-fitting, the impacts are often small. Some theoretical studies have analyzed the implicit regularization effect of stochastic gradient descent (SGD) on simple machine learning models with certain assumptions. However, how it behaves practically in state-of-the-art models and real-world datasets is still unknown. To bridge this gap, we study the role of SGD implicit regularization in deep learning systems. We show pure SGD tends to converge to minimas that have better generalization performances in multiple natural language processing (NLP) tasks. This phenomenon coexists with dropout, an explicit regularizer. In addition, neural network's finite learning capability does not impact the intrinsic nature of SGD's implicit regularization effect. Specifically, under limited training samples or with certain corrupted labels, the implicit regularization effect remains strong. We further analyze the stability by varying the weight initialization range. We corroborate these experimental findings with a decision boundary visualization using a 3-layer neural network for interpretation. Altogether, our work enables a deepened understanding on how implicit regularization affects the deep learning model and sheds light on the future study of the over-parameterized model's generalization ability.

References in corpus (8)

• Adam: A Method for Stochastic Optimization
• ADADELTA: An Adaptive Learning Rate Method
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
• Convolutional Neural Networks for Sentence Classification
• Understanding deep learning requires rethinking generalization
• Exact solutions to the nonlinear dynamics of learning in deep linear neural networks
• Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales
• On the Implicit Bias of Dropout

Cited by in corpus (4)

• Structure Probing Neural Network Deflation
• Reproducing Activation Function for Deep Learning
• The Discovery of Dynamics via Linear Multistep Methods and Deep Learning: Error Estimation
• Second-order Information in First-order Optimization Methods