Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity

Jingzhao Zhang, Tianxing He, Suvrit Sra, Ali Jadbabaie. Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, 2020. [doi]

@inproceedings{ZhangHSJ20,
  title = {Why Gradient Clipping Accelerates Training: A Theoretical Justification for Adaptivity},
  author = {Jingzhao Zhang and Tianxing He and Suvrit Sra and Ali Jadbabaie},
  year = {2020},
  url = {https://openreview.net/forum?id=BJgnXpVYwS},
  researchr = {https://researchr.org/publication/ZhangHSJ20},
  cites = {0},
  citedby = {0},
  booktitle = {8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020},
  publisher = {OpenReview.net},
}