Alternating Synthetic and Real Gradients for Neural Language Modeling
This work addresses a known bottleneck in sequence modeling for NLP researchers, but it appears incremental as it builds on existing gradient methods.
The paper tackles the problem of training recurrent neural networks for language modeling by combining synthetic and real gradients, demonstrating effectiveness through alternating training with periodic warm restarts.
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.