@inproceedings{23eae60b082e459f83908275f758cfe7,
title = "Autoclip: Adaptive gradient clipping for source separation networks",
abstract = "Clipping the gradient is a known approach to improving gradient descent, but requires hand selection of a clipping threshold hyperparameter. We present AutoClip, a simple method for automatically and adaptively choosing a gradient clipping threshold, based on the history of gradient norms observed during training. Experimental results show that applying Au-toClip results in improved generalization performance for audio source separation networks. Observation of the training dynamics of a separation network trained with and without AutoClip show that AutoClip guides optimization into smoother parts of the loss landscape. AutoClip is very simple to implement and can be integrated readily into a variety of applications across multiple domains.",
keywords = "Audio source separation, Computer audition, Deep learning, Optimization",
author = "Prem Seetharaman and Gordon Wichern and Bryan Pardo and Roux, {Jonathan Le}",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 30th IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2020 ; Conference date: 21-09-2020 Through 24-09-2020",
year = "2020",
month = sep,
doi = "10.1109/MLSP49062.2020.9231926",
language = "English (US)",
series = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",
publisher = "IEEE Computer Society",
booktitle = "Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020",
address = "United States",
}