Related papers: SAM operates far from home: eigenvalue regularizat…
Despite attaining high empirical generalization, the sharpness of models trained with sharpness-aware minimization (SAM) do not always correlate with generalization error. Instead of viewing SAM as minimizing sharpness to improve…
The self-attention mechanism (SAM) is widely used in various fields of artificial intelligence and has successfully boosted the performance of different models. However, current explanations of this mechanism are mainly based on intuitions…
A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…
Decentralized stochastic gradient descent (D-SGD) allows collaborative learning on massive devices simultaneously without the control of a central server. However, existing theories claim that decentralization invariably undermines…
Sharpness-Aware Minimization (SAM) enhances generalization by minimizing the maximum training loss within a predefined neighborhood around the parameters. However, its practical implementation approximates this as gradient ascent(s)…
Sharpness-aware minimization (SAM) has been shown to improve the generalization of neural networks. However, each SAM update requires \emph{sequentially} computing two gradients, effectively doubling the per-iteration cost compared to base…
In gradient descent dynamics of neural networks, the top eigenvalue of the loss Hessian (sharpness) displays a variety of robust phenomena throughout training. This includes early time regimes where the sharpness may decrease during early…
Sharpness-Aware Minimization (SAM) has emerged as a promising approach for effectively reducing the generalization error. However, SAM incurs twice the computational cost compared to base optimizer (e.g., SGD). We propose Asymptotic…
Sharpness-aware minimization (SAM) is to improve model generalization by searching for flat minima in the loss landscape. The SAM update consists of one step for computing the perturbation and the other for computing the update gradient.…
When training neural networks with full-batch gradient descent (GD) and step size $\eta$, the largest eigenvalue of the Hessian -- the sharpness $S(\boldsymbol{\theta})$ -- rises to $2/\eta$ and hovers there, a phenomenon termed the Edge of…
The generalization performance of deep neural networks (DNNs) is a critical factor in achieving robust model behavior on unseen data. Recent studies have highlighted the importance of sharpness-based measures in promoting generalization by…
To fully uncover the great potential of deep neural networks (DNNs), various learning algorithms have been developed to improve the model's generalization ability. Recently, sharpness-aware minimization (SAM) establishes a generic scheme…
This paper rethinks Sharpness-Aware Minimization (SAM), which is originally formulated as a zero-sum game where the weights of a network and a bounded perturbation try to minimize/maximize, respectively, the same differentiable loss. To…
Recent findings by Cohen et al., 2021, demonstrate that when training neural networks using full-batch gradient descent with a step size of $\eta$, the largest eigenvalue $\lambda_{\max}$ of the full-batch Hessian consistently stabilizes…
Sharpness-aware minimization (SAM) has been instrumental in improving deep neural network training by minimizing both the training loss and the sharpness of the loss landscape, leading the model into flatter minima that are associated with…
Network quantization is a dominant paradigm of model compression. However, the abrupt changes in quantized weights during training often lead to severe loss fluctuations and result in a sharp loss landscape, making the gradients unstable…
Generalization analyses of deep learning typically assume that the training converges to a fixed point. But, recent results indicate that in practice, the weights of deep neural networks optimized with stochastic gradient descent often…
Empirically, modern deep learning training often occurs at the Edge of Stability (EoS), where the sharpness of the loss exceeds the threshold below which classical convergence analysis applies. Despite recent progress, existing theoretical…
Fine-tuning large pretrained language models on a limited training corpus usually suffers from poor generalization. Prior works show that the recently-proposed sharpness-aware minimization (SAM) optimization method can improve the model…
Recent findings (e.g., arXiv:2103.00065) demonstrate that modern neural networks trained by full-batch gradient descent typically enter a regime called Edge of Stability (EOS). In this regime, the sharpness, i.e., the maximum Hessian…