Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization

• URL: http://arxiv.org/abs/2508.04950v1
• Date: Thu, 07 Aug 2025 00:33:00 GMT
• Title: Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization
• Authors: Wei Liu, Anweshit Panda, Ujwal Pandey, Christopher Brissette, Yikang Shen, George M. Slota, Naigang Wang, Jie Chen, Yangyang Xu,
• Abstract summary: We design two compressed decentralized algorithms for solving non-compression heterogeneity optimization under two different scenarios.<n>Both algorithms adopt a momentum technique to achieve fast convergence and a message-speed technique to save communication costs.<n> Superior empirical performance is observed over state-of-the-art methods on deep neural networks (DNNs) and Transformers.
• Score: 20.588374906635256
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we design two compressed decentralized algorithms for solving nonconvex stochastic optimization under two different scenarios. Both algorithms adopt a momentum technique to achieve fast convergence and a message-compression technique to save communication costs. Though momentum acceleration and compressed communication have been used in literature, it is highly nontrivial to theoretically prove the effectiveness of their composition in a decentralized algorithm that can maintain the benefits of both sides, because of the need to simultaneously control the consensus error, the compression error, and the bias from the momentum gradient. For the scenario where gradients are bounded, our proposal is a compressed decentralized adaptive method. To the best of our knowledge, this is the first decentralized adaptive stochastic gradient method with compressed communication. For the scenario of data heterogeneity without bounded gradients, our proposal is a compressed decentralized heavy-ball method, which applies a gradient tracking technique to address the challenge of data heterogeneity. Notably, both methods achieve an optimal convergence rate, and they can achieve linear speed up and adopt topology-independent algorithmic parameters within a certain regime of the user-specified error tolerance. Superior empirical performance is observed over state-of-the-art methods on training deep neural networks (DNNs) and Transformers.

Related papers

• Boosting the Performance of Decentralized Federated Learning via Catalyst Acceleration [66.43954501171292]
  We introduce Catalyst Acceleration and propose an acceleration Decentralized Federated Learning algorithm called DFedCata. DFedCata consists of two main components: the Moreau envelope function, which addresses parameter inconsistencies, and Nesterov's extrapolation step, which accelerates the aggregation phase. Empirically, we demonstrate the advantages of the proposed algorithm in both convergence speed and generalization performance on CIFAR10/100 with various non-iid data distributions.
  arXiv  Detail & Related papers  (2024-10-09T06:17:16Z)
• Flattened one-bit stochastic gradient descent: compressed distributed optimization with controlled variance [55.01966743652196]
  We propose a novel algorithm for distributed gradient descent (SGD) with compressed gradient communication in the parameter-server framework. Our gradient compression technique, named flattened one-bit gradient descent (FO-SGD), relies on two simple algorithmic ideas.
  arXiv  Detail & Related papers  (2024-05-17T21:17:27Z)
• On the Communication Complexity of Decentralized Bilevel Optimization [40.45379954138305]
  We propose two novel decentralized bilevel gradient descent algorithms based on simultaneous and alternating update strategies. Our algorithms can achieve faster convergence rates and lower communication costs than existing methods. This is the first time such favorable theoretical results have been achieved with mild assumptions in the heterogeneous setting.
  arXiv  Detail & Related papers  (2023-11-19T14:56:26Z)
• On Arbitrary Compression for Decentralized Consensus and Stochastic Optimization over Directed Networks [0.6526824510982799]
  We propose an iterative-based algorithm that compresses messages according to a desired compression ratio. Contrary to existing literature allow arbitrary compression ratios. We show explicit convergence rates for decentralized optimization problems on smooth functions.
  arXiv  Detail & Related papers  (2022-04-18T04:41:56Z)
• On Accelerating Distributed Convex Optimizations [0.0]
  This paper studies a distributed multi-agent convex optimization problem. We show that the proposed algorithm converges linearly with an improved rate of convergence than the traditional and adaptive gradient-descent methods. We demonstrate our algorithm's superior performance compared to prominent distributed algorithms for solving real logistic regression problems.
  arXiv  Detail & Related papers  (2021-08-19T13:19:54Z)
• A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free! [72.31332210635524]
  Decentralized optimization methods enable on-device training of machine learning models without a central coordinator. We propose a new randomized first-order method which tackles the communication bottleneck by applying randomized compression operators. We prove that our method can solve the problems without any increase in the number of communications compared to the baseline.
  arXiv  Detail & Related papers  (2020-11-03T13:35:53Z)
• Linear Convergent Decentralized Optimization with Compression [50.44269451541387]
  Existing decentralized algorithms with compression mainly focus on compressing DGD-type algorithms. Motivated by primal-dual algorithms, this paper proposes first underlineLinunderlineEAr convergent. underlineDecentralized with compression, LEAD.
  arXiv  Detail & Related papers  (2020-07-01T04:35:00Z)
• Cogradient Descent for Bilinear Optimization [124.45816011848096]
  We introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent. Our algorithm is applied to solve problems with one variable under the sparsity constraint.
  arXiv  Detail & Related papers  (2020-06-16T13:41:54Z)
• IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method [64.15649345392822]
  We introduce a framework for designing primal methods under the decentralized optimization setting where local functions are smooth and strongly convex. Our approach consists of approximately solving a sequence of sub-problems induced by the accelerated augmented Lagrangian method. When coupled with accelerated gradient descent, our framework yields a novel primal algorithm whose convergence rate is optimal and matched by recently derived lower bounds.
  arXiv  Detail & Related papers  (2020-06-11T18:49:06Z)

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.