DeepStability: A Study of Unstable Numerical Methods and Their Solutions in Deep Learning

Eliska Kloberdanz, Kyle G. Kloberdanz, Wei Le. DeepStability: A Study of Unstable Numerical Methods and Their Solutions in Deep Learning. In 44th IEEE/ACM 44th International Conference on Software Engineering, ICSE 2022, Pittsburgh, PA, USA, May 25-27, 2022. pages 586-597, IEEE, 2022. [doi]

@inproceedings{KloberdanzKL22,
  title = {DeepStability: A Study of Unstable Numerical Methods and Their Solutions in Deep Learning},
  author = {Eliska Kloberdanz and Kyle G. Kloberdanz and Wei Le},
  year = {2022},
  doi = {10.1145/3510003.3510095},
  url = {https://doi.org/10.1145/3510003.3510095},
  researchr = {https://researchr.org/publication/KloberdanzKL22},
  cites = {0},
  citedby = {0},
  pages = {586-597},
  booktitle = {44th IEEE/ACM 44th International Conference on Software Engineering, ICSE 2022, Pittsburgh, PA, USA, May 25-27, 2022},
  publisher = {IEEE},
  isbn = {978-1-4503-9221-1},
}