Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling

by   Zhe Gan, et al.

Recurrent neural networks (RNNs) have shown promising performance for language modeling. However, traditional training of RNNs using back-propagation through time often suffers from overfitting. One reason for this is that stochastic optimization (used for large training sets) does not provide good estimates of model uncertainty. This paper leverages recent advances in stochastic gradient Markov Chain Monte Carlo (also appropriate for large training sets) to learn weight uncertainty in RNNs. It yields a principled Bayesian learning algorithm, adding gradient noise during training (enhancing exploration of the model-parameter space) and model averaging when testing. Extensive experiments on various RNN models and across a broad range of applications demonstrate the superiority of the proposed approach over stochastic optimization.


Bayesian Recurrent Neural Networks

In this work we explore a straightforward variational Bayes scheme for R...

Training Language Models Using Target-Propagation

While Truncated Back-Propagation through Time (BPTT) is the most popular...

Neural Networks Compression for Language Modeling

In this paper, we consider several compression techniques for the langua...

Ensemble Neural Networks (ENN): A gradient-free stochastic method

In this study, an efficient stochastic gradient-free method, the ensembl...

Alternating Synthetic and Real Gradients for Neural Language Modeling

Training recurrent neural networks (RNNs) with backpropagation through t...

Regularizing RNNs by Stabilizing Activations

We stabilize the activations of Recurrent Neural Networks (RNNs) by pena...

EGRU: Event-based GRU for activity-sparse inference and learning

The scalability of recurrent neural networks (RNNs) is hindered by the s...