Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity

Cite

Text

Zhang et al. "Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity." International Conference on Learning Representations, 2020.

Markdown

[Zhang et al. "Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity." International Conference on Learning Representations, 2020.](https://mlanthology.org/iclr/2020/zhang2020iclr-gradient/)

BibTeX

@inproceedings{zhang2020iclr-gradient,
  title     = {{Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity}},
  author    = {Zhang, Jingzhao and He, Tianxing and Sra, Suvrit and Jadbabaie, Ali},
  booktitle = {International Conference on Learning Representations},
  year      = {2020},
  url       = {https://mlanthology.org/iclr/2020/zhang2020iclr-gradient/}
}