An SDE for Modeling SAM: Theory and Insights
Autor: | Compagnoni, Enea Monzio, Biggio, Luca, Orvieto, Antonio, Proske, Frank Norbert, Kersting, Hans, Lucchi, Aurelien |
---|---|
Rok vydání: | 2023 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | We study the SAM (Sharpness-Aware Minimization) optimizer which has recently attracted a lot of interest due to its increased performance over more classical variants of stochastic gradient descent. Our main contribution is the derivation of continuous-time models (in the form of SDEs) for SAM and two of its variants, both for the full-batch and mini-batch settings. We demonstrate that these SDEs are rigorous approximations of the real discrete-time algorithms (in a weak sense, scaling linearly with the learning rate). Using these models, we then offer an explanation of why SAM prefers flat minima over sharp ones~--~by showing that it minimizes an implicitly regularized loss with a Hessian-dependent noise structure. Finally, we prove that SAM is attracted to saddle points under some realistic conditions. Our theoretical results are supported by detailed experiments. Comment: Accepted at ICML 2023 (Poster) |
Databáze: | arXiv |
Externí odkaz: |