Papers › AutoClip: Adaptive Gradient Clipping for Source Separation Networks

AutoClip: Adaptive Gradient Clipping for Source Separation Networks

25 Jul 2020arXiv:2007.14469archive 2025-07-28

Prem Seetharaman, Gordon Wichern, Bryan Pardo, Jonathan Le Roux

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 AutoClip 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.

PaperPDFCode

Code

pseeth/autoclip officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Audio Source Separation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Gradient Clipping

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections