The paper investigates why the SCAFFOLD algorithm, designed to be robust to data heterogeneity in federated learning, often underperforms compared to the simpler FedAvg. It identifies the presence of Edge of Stability (EoS) dynamics and progressive sharpening as key factors, showing that both algorithms exhibit EoS behavior across various architectures and hyperparameters. Crucially, the study finds that at the EoS, SCAFFOLD’s ability to estimate the global gradient deteriorates, as indicated by a weakened correlation between sharpness and gradient estimation error, explaining its limited practical advantage.
By Anant Khandelwal, Michael Crawshaw, Mingrui Liu
arXiv:2505. 11304v4 Announce Type: replace-cross Abstract: Federated learning (FL) commonly involves clients with diverse communication and computational capabilities.
By Shudi Weng, Chao Ren, Ming Xiao, Mikael Skoglund
arXiv:2301. 06308v2 Announce Type: replace-cross Abstract: Sharpness-aware minimization (SAM) is a training method that seeks to find flat minima in deep learning, resulting in state-of-the-art performance across various domains.
By Hoki Kim, Jinseong Park, Yujin Choi, Jaewook Lee
arXiv:2606. 04212v1 Announce Type: new Abstract: Existing analyses of the edge of stability (EoS) treat it as a global property of optimization.
By Shauna Kwag, Anakha Ganesh, Tomaso Poggio, Pierfrancesco Beneventano
The paper introduces Batched SGD, a variant that groups online samples into epochs and performs a single update per epoch using a low‑variance gradient estimate. This batching approach allows a straightforward high‑probability analysis without restrictive assumptions or auxiliary sequences, yielding near‑optimal rates for both strongly convex and non‑convex objectives under standard smoothness and sub‑Gaussian noise conditions. The authors also extend the method to federated learning, providing the first high‑probability guarantees with logarithmic communication complexity, linear speedup in the number of agents, and robustness to data heterogeneity.
By Feng Zhu, Robert W. Heath Jr., Aritra Mitra
arXiv:2605. 29547v2 Announce Type: replace-cross Abstract: Deep learning optimization relies heavily on the assumption of smooth loss landscapes, a condition systematically violated by modern architectures due to non-smooth components such as ReLU activations and quantization operators.
By Ruoran Xu, Borong She, Xiaobo Jin, Qiufeng Wang
arXiv:2606. 18080v1 Announce Type: new Abstract: Gradient descent in deep learning may operate at the edge of stability (EoS), a regime in which the largest eigenvalue of the loss Hessian hovers near the stability threshold $2/\eta$, where $\eta$ is the learning rate.
By Pierre Marion
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:2510. 03164v2 Announce Type: replace Abstract: Learning rate warm-up -- increasing the learning rate at the beginning of training -- has become a ubiquitous heuristic in modern deep learning, yet its theoretical foundations remain poorly understood.
By Foivos Alimisis, Rustem Islamov, Aurelien Lucchi
Sharpness-Aware Minimization (SAM) improves generalization by seeking parameters whose loss is robust to local adversarial perturbations, but the quantitative mechanism underlying its implicit bias toward flat minima remains unclear. In particular, the perturbation radius $ρ$ is typically treated as an isolated tuning parameter, despite defining the neighborhood in which SAM measures sharpness.
arXiv:2608. 03197v1 Announce Type: new Abstract: Sharpness-Aware Minimization (SAM) improves generalization by seeking parameters whose loss is robust to local adversarial perturbations, but the quantitative mechanism underlying its implicit bias toward flat minima remains unclear.
By Jiaxin Deng, Junbiao Pang
arXiv:2606. 06722v1 Announce Type: new Abstract: The training of neural networks often entails objective functions that are not globally $L$-smooth.
By Leonardo Galli, Curtis Fox, Wiebke Bartolomaeus, Mark Schmidt, Holger Rauhut