Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable Programming

Fei Wang; James Decker; Xilun Wu; Gregory Essertel; Tiark Rompf

NeurIPS 2018poster59 citations

Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable Programming

Fei Wang, James Decker, Xilun Wu, Gregory Essertel, Tiark Rompf

Abstract

Training of deep learning models depends on gradient descent and end-to-end differentiation. Under the slogan of differentiable programming, there is an increasing demand for efficient automatic gradient computation for emerging network architectures that incorporate dynamic control flow, especially in NLP.

BibTeX

@inproceedings{NEURIPS2018_34e15776,
 author = {Wang, Fei and Decker, James and Wu, Xilun and Essertel, Gregory and Rompf, Tiark},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable Programming},
 url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/34e157766f31db3d2099831d348a7933-Paper.pdf},
 volume = {31},
 year = {2018}
}