CEDAS: A Compressed Decentralized Stochastic Gradient Method with Improved Convergence

• URL: http://arxiv.org/abs/2301.05872v3
• Date: Sun, 29 Sep 2024 03:04:49 GMT
• Title: CEDAS: A Compressed Decentralized Stochastic Gradient Method with Improved Convergence
• Authors: Kun Huang, Shi Pu,
• Abstract summary: In this paper, we consider solving the distributed optimization problem under the communication restricted setting. We show the method over com-pressed exact diffusion termed CEDAS" In particular, when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when when
• Score: 9.11726703830074
• License:
• Abstract: In this paper, we consider solving the distributed optimization problem over a multi-agent network under the communication restricted setting. We study a compressed decentralized stochastic gradient method, termed ``compressed exact diffusion with adaptive stepsizes (CEDAS)", and show the method asymptotically achieves comparable convergence rate as centralized { stochastic gradient descent (SGD)} for both smooth strongly convex objective functions and smooth nonconvex objective functions under unbiased compression operators. In particular, to our knowledge, CEDAS enjoys so far the shortest transient time (with respect to the graph specifics) for achieving the convergence rate of centralized SGD, which behaves as $\mathcal{O}(n{C^3}/(1-\lambda_2)^{2})$ under smooth strongly convex objective functions, and $\mathcal{O}(n^3{C^6}/(1-\lambda_2)^4)$ under smooth nonconvex objective functions, where $(1-\lambda_2)$ denotes the spectral gap of the mixing matrix, and $C>0$ is the compression-related parameter. In particular, CEDAS exhibits the shortest transient times when $C < \mathcal{O}(1/(1 - \lambda_2)^2)$, which is common in practice. Numerical experiments further demonstrate the effectiveness of the proposed algorithm.

Related papers

• 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)
• Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems [56.86067111855056]
  We consider clipped optimization problems with heavy-tailed noise with structured density. We show that it is possible to get faster rates of convergence than $mathcalO(K-(alpha - 1)/alpha)$, when the gradients have finite moments of order. We prove that the resulting estimates have negligible bias and controllable variance.
  arXiv  Detail & Related papers  (2023-11-07T17:39:17Z)
• On Convergence of Incremental Gradient for Non-Convex Smooth Functions [63.51187646914962]
  In machine learning and network optimization, algorithms like shuffle SGD are popular due to minimizing the number of misses and good cache. This paper delves into the convergence properties SGD algorithms with arbitrary data ordering.
  arXiv  Detail & Related papers  (2023-05-30T17:47:27Z)
• Zero-Order One-Point Estimate with Distributed Stochastic Gradient-Tracking Technique [23.63073074337495]
  We consider a distributed multi-agent optimization problem where each agent holds a local objective function that is smooth and convex. We extend the distributed gradient-tracking method to the bandit setting where we don't have an estimate of the gradient. We analyze the convergence of this novel technique for smooth and convex objectives using approximation tools.
  arXiv  Detail & Related papers  (2022-10-11T17:04:45Z)
• Optimal Extragradient-Based Bilinearly-Coupled Saddle-Point Optimization [116.89941263390769]
  We consider the smooth convex-concave bilinearly-coupled saddle-point problem, $min_mathbfxmax_mathbfyF(mathbfx) + H(mathbfx,mathbfy)$, where one has access to first-order oracles for $F$, $G$ as well as the bilinear coupling function $H$. We present a emphaccelerated gradient-extragradient (AG-EG) descent-ascent algorithm that combines extragrad
  arXiv  Detail & Related papers  (2022-06-17T06:10:20Z)
• Sharper Convergence Guarantees for Asynchronous SGD for Distributed and Federated Learning [77.22019100456595]
  We show a training algorithm for distributed computation workers with varying communication frequency. In this work, we obtain a tighter convergence rate of $mathcalO!!!(sigma2-2_avg!! . We also show that the heterogeneity term in rate is affected by the average delay within each worker.
  arXiv  Detail & Related papers  (2022-06-16T17:10:57Z)
• Mean-Square Analysis with An Application to Optimal Dimension Dependence of Langevin Monte Carlo [60.785586069299356]
  This work provides a general framework for the non-asymotic analysis of sampling error in 2-Wasserstein distance. Our theoretical analysis is further validated by numerical experiments.
  arXiv  Detail & Related papers  (2021-09-08T18:00:05Z)
• Improving the Transient Times for Distributed Stochastic Gradient Methods [5.215491794707911]
  We study a distributed gradient algorithm, called exact diffusion adaptive stepsizes (EDAS) We show EDAS achieves the same network independent convergence rate as centralized gradient descent (SGD) To the best of our knowledge, EDAS achieves the shortest time when the average of the $n$ cost functions is strongly convex.
  arXiv  Detail & Related papers  (2021-05-11T08:09:31Z)
• A Variance Controlled Stochastic Method with Biased Estimation for Faster Non-convex Optimization [0.0]
  We propose a new technique, em variance controlled gradient (VCSG), to improve the performance of the reduced gradient (SVRG) $lambda$ is introduced in VCSG to avoid over-reducing a variance by SVRG. $mathcalO(min1/epsilon3/2,n1/4/epsilon)$ number of gradient evaluations, which improves the leading gradient complexity.
  arXiv  Detail & Related papers  (2021-02-19T12:22:56Z)
• S-ADDOPT: Decentralized stochastic first-order optimization over directed graphs [16.96562173221624]
  Decentralized convex optimization is proposed to minimize a sum of smooth and strongly cost functions when the functions are distributed over a directed network nodes. In particular, we propose thetextbftextttS-ADDOPT algorithm that assumes a first-order oracle at each node. For decaying step-sizes$mathcalO (1/k)$, we show thattextbfttS-ADDOPT reaches the exact solution subly at$mathcalO (1/k)$ and its convergence is networkally-independent
  arXiv  Detail & Related papers  (2020-05-15T21:14:22Z)
• Stochastic gradient-free descents [8.663453034925363]
  We propose gradient-free methods and accelerated gradients with momentum for solving optimization problems. We analyze the convergence behavior of these methods under the mean-variance framework.
  arXiv  Detail & Related papers  (2019-12-31T13:56:36Z)

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.