How Edge of Stability Hinders SCAFFOLD in Federated Optimization

• URL: http://arxiv.org/abs/2608.25873v1
• Date: Wed, 26 Aug 2026 14:45:21 GMT
• Title: How Edge of Stability Hinders SCAFFOLD in Federated Optimization
• Abstract summary: We show that SCAFFOLD does not usually outperform the much simpler FedAvg in practice.<n>We propose that this gap is due to the presence of Edge of Stability (EoS) and progressive sharpening in federated optimization.<n>We observe that SCAFFOLD's ability to estimate the gradient of the global objective is severely degraded at the EoS.
• Score: 48.656242232026756
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In federated learning, it is well known that heterogeneous data can (in theory) slow down optimization, and much effort has been directed at designing optimization algorithms that are unaffected by data heterogeneity, such as the SCAFFOLD algorithm. Yet, despite strong theoretical guarantees, SCAFFOLD does not usually outperform the much simpler FedAvg in practice. In this work, we propose that this gap is due to the presence of Edge of Stability (EoS) and progressive sharpening in federated optimization, supported by extensive empirical probing. First, we find that EoS-like dynamics occur with both FedAvg and SCAFFOLD under a variety of architectures and hyperparameters. We observe that the equilibrium value of the sharpness is inversely proportional to the learning rate (as in GD), and interestingly, the degree of data heterogeneity (but not the number of local steps) also affects the equilibrium value. Most importantly, we observe that SCAFFOLD's ability to estimate the gradient of the global objective is severely degraded at the EoS, as measured by the correlation between sharpness and SCAFFOLD's error in estimating the global gradient along the optimization trajectory. This suggests a mechanism for SCAFFOLD's lackluster performance in deep learning: with high sharpness at the EoS, SCAFFOLD cannot reliably estimate the global gradient.

Related papers

• Taming the Instability: A Robust Second-Order Optimizer for Federated Learning over Non-IID Data [77.19117648492104]
  We present Federated Robust Curvature Optimization (FedRCO), a novel second-order optimization framework designed to improve convergence speed and reduce communication cost.<n>FedRCO addresses these challenges by integrating an efficient approximate curvature with a provable stability mechanism.<n>We show that FedRCO achieves superior robustness against diverse non-IID scenarios while achieving higher accuracy and faster convergence than both state-of-the-art first-order and second-order methods.
  arXiv  Detail & Related papers  (2026-03-30T11:37:46Z)
• Gradient Compression May Hurt Generalization: A Remedy by Synthetic Data Guided Sharpness Aware Minimization [42.77143251031899]
  gradient compression in federated learning (FL) enjoys significant improvement in communication efficiency with negligible performance degradation.<n>We propose FedSynSAM, which leverages the global model trajectory to construct synthetic data and facilitates an accurate estimation of the global perturbation.
  arXiv  Detail & Related papers  (2026-02-12T05:08:49Z)
• NDCG-Consistent Softmax Approximation with Accelerated Convergence [67.10365329542365]
  We propose novel loss formulations that align directly with ranking metrics.<n>We integrate the proposed RG losses with the highly efficient Alternating Least Squares (ALS) optimization method.<n> Empirical evaluations on real-world datasets demonstrate that our approach achieves comparable or superior ranking performance.
  arXiv  Detail & Related papers  (2025-06-11T06:59:17Z)
• Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum [78.27945336558987]
  Decentralized server (DFL) eliminates reliance on client-client architecture.<n>Non-smooth regularization is often incorporated into machine learning tasks.<n>We propose a novel novel DNCFL algorithm to solve these problems.
  arXiv  Detail & Related papers  (2025-04-17T08:32:25Z)
• Federated Smoothing Proximal Gradient for Quantile Regression with Non-Convex Penalties [3.269165283595478]
  Distributed sensors in the internet-of-things (IoT) generate vast amounts of sparse data. We propose a federated smoothing proximal gradient (G) algorithm that integrates a smoothing mechanism with the view, thereby both precision and computational speed.
  arXiv  Detail & Related papers  (2024-08-10T21:50:19Z)
• Achieving Constraints in Neural Networks: A Stochastic Augmented Lagrangian Approach [49.1574468325115]
  Regularizing Deep Neural Networks (DNNs) is essential for improving generalizability and preventing overfitting. We propose a novel approach to DNN regularization by framing the training process as a constrained optimization problem. We employ the Augmented Lagrangian (SAL) method to achieve a more flexible and efficient regularization mechanism.
  arXiv  Detail & Related papers  (2023-10-25T13:55:35Z)
• On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data [39.600069116159695]
  Existing theory predicts that data heterogeneity will degrade the performance of the Federated Averaging (FedAvg) algorithm in federated learning. This paper explains the seemingly unreasonable effectiveness of FedAvg that contradicts the previous theoretical predictions.
  arXiv  Detail & Related papers  (2022-06-09T18:25:25Z)
• CAFE: Learning to Condense Dataset by Aligning Features [72.99394941348757]
  We propose a novel scheme to Condense dataset by Aligning FEatures (CAFE) At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art.
  arXiv  Detail & Related papers  (2022-03-03T05:58:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.