Alternating Synthetic and Real Gradients for Neural Language Modeling

Abstract

Training recurrent neural networks (RNNs) with backpropagation through time (BPTT) has known drawbacks such as being difficult to capture longterm dependencies in sequences. Successful alternatives to BPTT have not yet been discovered. Recently, BP with synthetic gradients by a decoupled neural interface module has been proposed to replace BPTT for training RNNs. On the other hand, it has been shown that the representations learned with synthetic and real gradients are different though they are functionally identical. In this project, we explore ways of combining synthetic and real gradients with application to neural language modeling tasks. Empirically, we demonstrate the effectiveness of alternating training with synthetic and real gradients after periodic warm restarts on language modeling tasks.

renew the ideas

References in corpus (7)

• SGDR: Stochastic Gradient Descent with Warm Restarts
• Pointer Sentinel Mixture Models
• Regularizing and Optimizing LSTM Language Models
• Quasi-Recurrent Neural Networks
• Decoupled Neural Interfaces using Synthetic Gradients
• Training Neural Networks Using Features Replay
• Understanding Synthetic Gradients and Decoupled Neural Interfaces