Parallelizing Linear Recurrent Neural Nets Over Sequence Length

Eric Martin,Chris Cundy

Published 2017 in International Conference on Learning Representations

ABSTRACT

Recurrent neural networks (RNNs) are widely used to model sequential data but their non-linear dependencies between sequence elements prevent parallelizing training over sequence length. We show the training of RNNs with only linear sequential dependencies can be parallelized over the sequence length using the parallel scan algorithm, leading to rapid training on long sequences even with small minibatch size. We develop a parallel linear recurrence CUDA kernel and show that it can be applied to immediately speed up training and inference of several state of the art RNN architectures by up to 9x. We abstract recent work on linear RNNs into a new framework of linear surrogate RNNs and develop a linear surrogate model for the long short-term memory unit, the GILR-LSTM, that utilizes parallel linear recurrence. We extend sequence learning to new extremely long sequence regimes that were previously out of reach by successfully training a GILR-LSTM on a synthetic sequence classification task with a one million timestep dependency.

PUBLICATION RECORD

  • Publication year

    2017

  • Venue

    International Conference on Learning Representations

  • Publication date

    2017-09-12

  • Fields of study

    Computer Science

  • Identifiers
  • External record

    Open on Semantic Scholar

  • Source metadata

    Semantic Scholar

CITATION MAP

EXTRACTION MAP

CLAIMS

  • No claims are published for this paper.

CONCEPTS

  • No concepts are published for this paper.

REFERENCES

Showing 1-21 of 21 references · Page 1 of 1

CITED BY

Showing 1-100 of 156 citing papers · Page 1 of 2