English

A Simple and Efficient Stochastic Rounding Method for Training Neural Networks in Low Precision

Machine Learning 2021-03-26 v1

Abstract

Conventional stochastic rounding (CSR) is widely employed in the training of neural networks (NNs), showing promising training results even in low-precision computations. We introduce an improved stochastic rounding method, that is simple and efficient. The proposed method succeeds in training NNs with 16-bit fixed-point numbers and provides faster convergence and higher classification accuracy than both CSR and deterministic rounding-to-the-nearest method.

Keywords

Cite

@article{arxiv.2103.13445,
  title  = {A Simple and Efficient Stochastic Rounding Method for Training Neural Networks in Low Precision},
  author = {Lu Xia and Martijn Anthonissen and Michiel Hochstenbach and Barry Koren},
  journal= {arXiv preprint arXiv:2103.13445},
  year   = {2021}
}
R2 v1 2026-06-24T00:31:54.749Z