Improved High-probability Convergence Guarantees of Decentralized SGD

• URL: http://arxiv.org/abs/2510.06141v1
• Date: Tue, 07 Oct 2025 17:15:08 GMT
• Title: Improved High-probability Convergence Guarantees of Decentralized SGD
• Authors: Aleksandar Armacki, Ali H. Sayed,
• Abstract summary: We show that $mathttDSGD$ converges in HP under the same conditions on the cost as in the mean-squared error (MSE) sense.<n>Our improved analysis yields linear-up in the number of users, demonstrating that $mathttDSGD$ maintains performance in the HP sense.
• Score: 74.39742894097348
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convergence in high-probability (HP) has been receiving increasing interest, due to its attractive properties, such as exponentially decaying tail bounds and strong guarantees for each individual run of an algorithm. While HP guarantees are extensively studied in centralized settings, much less is understood in the decentralized, networked setup. Existing HP studies in decentralized settings impose strong assumptions, like uniformly bounded gradients, or asymptotically vanishing noise, resulting in a significant gap between assumptions used to establish convergence in the HP and the mean-squared error (MSE) sense, even for vanilla Decentralized Stochastic Gradient Descent ($\mathtt{DSGD}$) algorithm. This is contrary to centralized settings, where it is known that $\mathtt{SGD}$ converges in HP under the same conditions on the cost function as needed to guarantee MSE convergence. Motivated by this observation, we revisit HP guarantees for $\mathtt{DSGD}$ in the presence of light-tailed noise. We show that $\mathtt{DSGD}$ converges in HP under the same conditions on the cost as in the MSE sense, removing uniformly bounded gradients and other restrictive assumptions, while simultaneously achieving order-optimal rates for both non-convex and strongly convex costs. Moreover, our improved analysis yields linear speed-up in the number of users, demonstrating that $\mathtt{DSGD}$ maintains strong performance in the HP sense and matches existing MSE guarantees. Our improved results stem from a careful analysis of the MGF of quantities of interest (norm-squared of gradient or optimality gap) and the MGF of the consensus gap between users' models. To achieve linear speed-up, we provide a novel result on the variance-reduction effect of decentralized methods in the HP sense and more fine-grained bounds on the MGF for strongly convex costs, which are both of independent interest.

Related papers

• Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs [55.77845440440496]
  Push-based decentralized communication enables optimization over communication networks, where information exchange may be asymmetric.<n>We develop a unified uniform-stability framework for the Gradient Push (SGP) algorithm.<n>A key technical ingredient is an imbalance-aware generalization bound through two quantities.
  arXiv  Detail & Related papers  (2026-02-24T05:32:03Z)
• Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level [18.723330586196997]
  We provide the first high-probability convergence analysis for DP with a fixed clipping level.<n>Our results show that, with a fixed clipping level, the method converges to a neighborhood optimal solution with a faster rate than the existing ones.<n>The neighborhood is balanced against the noise introduced by DP, providing a refined trade-off between convergence speed and privacy guarantees.
  arXiv  Detail & Related papers  (2025-07-31T12:48:29Z)
• Theory of Decentralized Robust Kernel-Based Learning [8.407288892993703]
  We propose a new robust kernel-based learning algorithm within the framework of reproducing kernel Hilbert spaces.<n>We show each local robust estimator generated from the decentralized algorithm can be utilized to approximate the regression function.<n>We provide rigorous selection rules for local sample size and show that, under properly selected step size and scaling parameter $sigma$, the decentralized robust algorithm can achieve optimal learning rates.
  arXiv  Detail & Related papers  (2025-06-05T16:30:05Z)
• Federated PCA and Estimation for Spiked Covariance Matrices: Optimal Rates and Efficient Algorithm [19.673557166734977]
  Federated Learning (FL) has gained significant recent attention in machine learning for its enhanced privacy and data security. This paper investigates federated PCA and estimation for spiked covariance matrices under distributed differential privacy constraints. We establish minimax rates of convergence, with a key finding that the central server's optimal rate is the harmonic mean of the local clients' minimax rates.
  arXiv  Detail & Related papers  (2024-11-23T21:57:50Z)
• Adaptive, Doubly Optimal No-Regret Learning in Strongly Monotone and Exp-Concave Games with Gradient Feedback [75.29048190099523]
  Online gradient descent (OGD) is well known to be doubly optimal under strong convexity or monotonicity assumptions. In this paper, we design a fully adaptive OGD algorithm, textsfAdaOGD, that does not require a priori knowledge of these parameters.
  arXiv  Detail & Related papers  (2023-10-21T18:38:13Z)
• Distributionally Robust Optimization with Bias and Variance Reduction [9.341215359733601]
  We show that Prospect, a gradient-based algorithm, enjoys linear convergence for smooth regularized losses. We also show that Prospect can converge 2-3$times$ faster than baselines such as gradient-based methods.
  arXiv  Detail & Related papers  (2023-10-21T00:03:54Z)
• DFedADMM: Dual Constraints Controlled Model Inconsistency for Decentralized Federated Learning [52.83811558753284]
  Decentralized learning (DFL) discards the central server and establishes a decentralized communication network. Existing DFL methods still suffer from two major challenges: local inconsistency and local overfitting.
  arXiv  Detail & Related papers  (2023-08-16T11:22:36Z)
• Utilising the CLT Structure in Stochastic Gradient based Sampling : Improved Analysis and Faster Algorithms [14.174806471635403]
  We consider approximations of sampling algorithms, such as Gradient Langevin Dynamics (SGLD) and the Random Batch Method (RBM) for Interacting Particle Dynamcs (IPD) We observe that the noise introduced by the approximation is nearly Gaussian due to the Central Limit Theorem (CLT) while the driving Brownian motion is exactly Gaussian. We harness this structure to absorb the approximation error inside the diffusion process, and obtain improved convergence guarantees for these algorithms.
  arXiv  Detail & Related papers  (2022-06-08T10:17:40Z)
• Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity [49.66890309455787]
  We introduce the expected co-coercivity condition, explain its benefits, and provide the first last-iterate convergence guarantees of SGDA and SCO. We prove linear convergence of both methods to a neighborhood of the solution when they use constant step-size. Our convergence guarantees hold under the arbitrary sampling paradigm, and we give insights into the complexity of minibatching.
  arXiv  Detail & Related papers  (2021-06-30T18:32:46Z)
• Distributional Robustness and Regularization in Reinforcement Learning [62.23012916708608]
  We introduce a new regularizer for empirical value functions and show that it lower bounds the Wasserstein distributionally robust value function. It suggests using regularization as a practical tool for dealing with $textitexternal uncertainty$ in reinforcement learning.
  arXiv  Detail & Related papers  (2020-03-05T19:56:23Z)

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.