Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum

• URL: http://arxiv.org/abs/2504.12742v1
• Date: Thu, 17 Apr 2025 08:32:25 GMT
• Title: Decentralized Nonconvex Composite Federated Learning with Gradient Tracking and Momentum
• Authors: Yuan Zhou, Xinli Shi, Xuelong Li, Jiachen Zhong, Guanghui Wen, Jinde Cao,
• Abstract summary: 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.
• Score: 78.27945336558987
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Decentralized Federated Learning (DFL) eliminates the reliance on the server-client architecture inherent in traditional federated learning, attracting significant research interest in recent years. Simultaneously, the objective functions in machine learning tasks are often nonconvex and frequently incorporate additional, potentially nonsmooth regularization terms to satisfy practical requirements, thereby forming nonconvex composite optimization problems. Employing DFL methods to solve such general optimization problems leads to the formulation of Decentralized Nonconvex Composite Federated Learning (DNCFL), a topic that remains largely underexplored. In this paper, we propose a novel DNCFL algorithm, termed \bf{DEPOSITUM}. Built upon proximal stochastic gradient tracking, DEPOSITUM mitigates the impact of data heterogeneity by enabling clients to approximate the global gradient. The introduction of momentums in the proximal gradient descent step, replacing tracking variables, reduces the variance introduced by stochastic gradients. Additionally, DEPOSITUM supports local updates of client variables, significantly reducing communication costs. Theoretical analysis demonstrates that DEPOSITUM achieves an expected $\epsilon$-stationary point with an iteration complexity of $\mathcal{O}(1/\epsilon^2)$. The proximal gradient, consensus errors, and gradient estimation errors decrease at a sublinear rate of $\mathcal{O}(1/T)$. With appropriate parameter selection, the algorithm achieves network-independent linear speedup without requiring mega-batch sampling. Finally, we apply DEPOSITUM to the training of neural networks on real-world datasets, systematically examining the influence of various hyperparameters on its performance. Comparisons with other federated composite optimization algorithms validate the effectiveness of the proposed method.

Related papers

• Non-Convex Optimization in Federated Learning via Variance Reduction and Adaptive Learning [13.83895180419626]
  This paper proposes a novel algorithm that leverages momentum-based variance reduction with adaptive learning to address non-epsilon settings across heterogeneous data.<n>We aim to overcome challenges related to variance, hinders efficiency, and the slow convergence from learning rate adjustments with heterogeneous data.
  arXiv  Detail & Related papers  (2024-12-16T11:02:38Z)
• Adaptive Consensus Gradients Aggregation for Scaled Distributed Training [6.234802839923543]
  We analyze the distributed gradient aggregation process through the lens of subspace optimization. Our method demonstrates improved performance over the ubiquitous averaging on multiple tasks while remaining extremely efficient in both communicational and computational complexity.
  arXiv  Detail & Related papers  (2024-11-06T08:16:39Z)
• Byzantine-resilient Federated Learning Employing Normalized Gradients on Non-IID Datasets [23.640506243685863]
  In practical federated learning (FLNGA) the presence of malicious attacks and data heterogeneity often introduces biases into the learning process. We propose a Normalized Gradient unit (Fed-M) model which normalizes uploaded local gradients to be before aggregation, achieving a time of $mathcalO(pM)$.
  arXiv  Detail & Related papers  (2024-08-18T16:50:39Z)
• 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)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time [45.72323731094864]
  In this paper, we study the optimality gap between two-layer ReLULU networks regularized with weight decay and their convex relaxations. Our study sheds new light on understanding why local methods work well.
  arXiv  Detail & Related papers  (2024-02-06T01:29:35Z)
• Stochastic Unrolled Federated Learning [85.6993263983062]
  We introduce UnRolled Federated learning (SURF), a method that expands algorithm unrolling to federated learning. Our proposed method tackles two challenges of this expansion, namely the need to feed whole datasets to the unrolleds and the decentralized nature of federated learning.
  arXiv  Detail & Related papers  (2023-05-24T17:26:22Z)
• Can Decentralized Stochastic Minimax Optimization Algorithms Converge Linearly for Finite-Sum Nonconvex-Nonconcave Problems? [56.62372517641597]
  Decentralized minimax optimization has been actively studied in the past few years due to its application in a wide range machine learning. This paper develops two novel decentralized minimax optimization algorithms for the non-strongly-nonconcave problem.
  arXiv  Detail & Related papers  (2023-04-24T02:19:39Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• Adaptive Self-supervision Algorithms for Physics-informed Neural Networks [59.822151945132525]
  Physics-informed neural networks (PINNs) incorporate physical knowledge from the problem domain as a soft constraint on the loss function. We study the impact of the location of the collocation points on the trainability of these models. We propose a novel adaptive collocation scheme which progressively allocates more collocation points to areas where the model is making higher errors.
  arXiv  Detail & Related papers  (2022-07-08T18:17:06Z)
• Accelerating Federated Edge Learning via Topology Optimization [41.830942005165625]
  Federated edge learning (FEEL) is envisioned as a promising paradigm to achieve privacy-preserving distributed learning. It consumes excessive learning time due to the existence of straggler devices. A novel topology-optimized federated edge learning (TOFEL) scheme is proposed to tackle the heterogeneity issue in federated learning.
  arXiv  Detail & Related papers  (2022-04-01T14:49:55Z)
• Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks [50.42141893913188]
  We study a distributed variable for large-scale AUC for a neural network as with a deep neural network. Our model requires a much less number of communication rounds and still a number of communication rounds in theory. Our experiments on several datasets show the effectiveness of our theory and also confirm our theory.
  arXiv  Detail & Related papers  (2020-05-05T18:08:23Z)

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.