Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees

Résumé

Gradient clipping is a popular modification to standard (stochastic) gradient descent, at every iteration limiting the gradient norm to a certain value $c >0$. It is widely used for example for stabilizing the training of deep learning models (Goodfellow et al., 2016), or for enforcing differential privacy (Abadi et al., 2016). Despite popularity and simplicity of the clipping mechanism, its convergence guarantees often require specific values of $c$ and strong noise assumptions. In this paper, we give convergence guarantees that show precise dependence on arbitrary clipping thresholds $c$ and show that our guarantees are tight with both deterministic and stochastic gradients. In particular, we show that (i) for deterministic gradient descent, the clipping threshold only affects the higher-order terms of convergence, (ii) in the stochastic setting convergence to the true optimum cannot be guaranteed under the standard noise assumption, even under arbitrary small step-sizes. We give matching upper and lower bounds for convergence of the gradient norm when running clipped SGD, and illustrate these results with experiments.
Fichier principal
Vignette du fichier
2305.01588.pdf (784.06 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04107297 , version 1 (26-05-2023)

Licence

Paternité

Identifiants

Citer

Anastasia Koloskova, Hadrien Hendrikx, Sebastian U. Stich. Revisiting Gradient Clipping: Stochastic bias and tight convergence guarantees. ICML 2023 - 40th International Conference on Machine Learning, Jul 2023, Honolulu, Hawaii,, United States. pp.1-19. ⟨hal-04107297⟩
129 Consultations
93 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More