The paper investigates whether flatter loss landscapes drive better generalization in the context of Grokking. It shows that sharpness‑aware minimization (SAM) alone does not reliably induce the transition to generalization, but when combined with weight decay, SAM can accelerate this transition up to four times faster. The authors provide a theoretical analysis using a minimal two‑layer ReLU model, demonstrating that flatness alone cannot distinguish memorizing from generalizing solutions, while weight decay favors generalization and a local stability window explains SAM’s effect.
By Mohnish Harwani
arXiv:2605. 05209v2 Announce Type: replace-cross Abstract: Flat minima are an account of why deep networks generalise.
By Michael Timothy Bennett
arXiv:2607. 06151v1 Announce Type: new Abstract: Generalization remains a pivotal challenge in deep learning, where traditional optimizers like Stochastic Gradient Descent (SGD) often converge to sharp minima, leading to overfitting and reduced performance on unseen data.
By Yao Fu, Chunxia Zhang, Junmin Liu, Yihang Jin, Haishan Ye, Yuanao Yang
arXiv:2602.01718v2 Announce Type: replace
Abstract: Predicting generalization from quantities available before target-test evaluation remains a central challenge in deep learning. The systematic benc...
By Sora Nakai, Youssef Fadhloun, Kacem Mathlouthi, Kotaro Yoshida, Ganesh Talluri, Ioannis Mitliagkas, Hiroki Naganuma
arXiv:2606. 20469v1 Announce Type: new Abstract: A widely held intuition in deep learning is that stochastic gradient descent (SGD) implicitly favors flat minima and that flat minima generalize better, but standard Euclidean measures of flatness such as the trace or maximum eigenvalue of the loss Hessian are not invariant under reparametrizations that preserve the network function, which undermines the theoretical foundations of this narrative.
By Md Sakir Ahmed, Kumaresh Sarmah, Hemen Dutta
arXiv:2606. 29043v1 Announce Type: new Abstract: Sharpness and complexity are two central factors in the generalization analysis of deep neural networks.
By Ziyu Cheng, Xitong Zhang, Longxiu Huang, Rongrong Wang
arXiv:2609.38540v1 Announce Type: new
Abstract: A valid curvature upper bound need not justify either a robustness certificate or an intervention on an intrinsic predictor property. We demonstrate th...
By Vicente Opazo, Jose Calatayud-Mateu, Cristobal Rojas, Cristian Buc Calderon
A common heuristic used to explain the generalization of first-order gradient methods on non-convex neural networks is that "flat interpolators generalize well" (Hochreiter and Schmidhuber, 1994; Keskar et al. , 2017), where flatness can be measured by the trace of the Hessian of the empirical loss.
arXiv:2606. 04429v1 Announce Type: cross Abstract: A common heuristic used to explain the generalization of first-order gradient methods on non-convex neural networks is that "flat interpolators generalize well" (Hochreiter and Schmidhuber, 1994; Keskar et al.
By Harsh Vardhan, Hossein Taheri, Arya Mazumdar
arXiv:2410.21582v4 Announce Type: replace-cross
Abstract: Large-scale pretrained models are widely leveraged as foundations for learning new specialized tasks via fine-tuning, with the goal of mainta...
By Jaedong Hwang, Brian Cheung, Zhang-Wei Hong, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete
arXiv:2606. 04409v1 Announce Type: cross Abstract: Modern deep neural networks usually have large parameter scales and nonlinear hierarchical structures, and they have achieved strong performance in computer vision.
By Luoyidi Zhou
arXiv:2505. 23866v2 Announce Type: replace Abstract: Deep neural networks have been increasingly used in safety-critical applications such as medical diagnosis and autonomous driving.
By Chengli Tan, Yubo Zhou, Haishan Ye, Guang Dai, Junmin Liu, Zengjie Song, Jiangshe Zhang, Zixiang Zhao, Yunda Hao, Yong Xu