Sharpness-Aware Minimization Can Hallucinate Minimizers
Sharpness-Aware Minimization (SAM) is widely used to seek flatter minima -- often linked to better generalization. In its standard implementation, SAM updates the current iterate using the loss gradient evaluated at a point perturbed by distance $ρ$ along the normalized gradient direction. We show that, for some choices of $ρ$, SAM can stall at points where this shifted (perturbed-point) gradient vanishes despite a nonzero original gradient, and therefore, they are not stationary points of the original loss. We call these points hallucinated minimizers, prove their existence under simple nonconvex landscape conditions (e.g., the presence of a local minimizer and a local maximizer), and establish sufficient conditions for local convergence of the SAM iterates to them. We corroborate this failure mode in neural network training and observe that it aligns with SAM's performance degradation often seen at large $ρ$. Finally, as a practical safeguard, we find that a short initial SGD warm-start before enabling SAM mitigates this failure mode and reduces sensitivity to the choice of $ρ$.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning
Model-agnostic meta learning (MAML) is currently one of the dominating approaches for few-shot meta-learning. Albeit its effectiveness, the optimization of MAML can be challenging due to the innate bilevel problem struct…
Meta-LearningmodelSharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization
Despite extensive studies, the underlying reason as to why overparameterized neural networks can generalize remains elusive. Existing theory shows that common stochastic optimizers prefer flatter minimizers of the traini…
Diversity-Aware Agnostic Ensemble of Sharpness Minimizers
There has long been plenty of theoretical and empirical evidence supporting the success of ensemble learning. Deep ensembles in particular take advantage of training randomness and expressivity of individual neural netwo…
DiversityEnsemble LearningModel Generalization: A Sharpness Aware Optimization Perspective
Sharpness-Aware Minimization (SAM) and adaptive sharpness-aware minimization (ASAM) aim to improve the model generalization. And in this project, we proposed three experiments to valid their generalization from the sharp…
modelvalidSALR: Sharpness-aware Learning Rates for Improved Generalization
In an effort to improve generalization in deep learning, we propose SALR: a sharpness-aware learning rate update technique designed to recover flat minimizers. Our method dynamically updates the learning rate of gradient…