Improved Analysis of the Accelerated Noisy Power Method with Applications to Decentralized PCA

• URL: http://arxiv.org/abs/2602.03682v1
• Date: Tue, 03 Feb 2026 16:03:11 GMT
• Title: Improved Analysis of the Accelerated Noisy Power Method with Applications to Decentralized PCA
• Authors: Pierre Aguié, Mathieu Even, Laurent Massoulié,
• Abstract summary: We analyze the Accelerated Noisy Power Method, an algorithm for Principal Component Analysis.<n>We show that our analysis is worst-case optimal, in the sense that the convergence rate cannot be improved.<n>This is the first decentralized algorithm for PCA with provably accelerated convergence.
• Score: 16.55513570548248
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We analyze the Accelerated Noisy Power Method, an algorithm for Principal Component Analysis in the setting where only inexact matrix-vector products are available, which can arise for instance in decentralized PCA. While previous works have established that acceleration can improve convergence rates compared to the standard Noisy Power Method, these guarantees require overly restrictive upper bounds on the magnitude of the perturbations, limiting their practical applicability. We provide an improved analysis of this algorithm, which preserves the accelerated convergence rate under much milder conditions on the perturbations. We show that our new analysis is worst-case optimal, in the sense that the convergence rate cannot be improved, and that the noise conditions we derive cannot be relaxed without sacrificing convergence guarantees. We demonstrate the practical relevance of our results by deriving an accelerated algorithm for decentralized PCA, which has similar communication costs to non-accelerated methods. To our knowledge, this is the first decentralized algorithm for PCA with provably accelerated convergence.

Related papers

• Accelerating Feedback-based Algorithms for Quantum Optimization Using Gradient Descent [6.852394426719304]
  Quantum Lyapunov Control (QLC) employs feedback-driven control laws that guarantee monotonic non-decreasing objective values.<n>We propose a hybrid method that incorporates per-layer gradient estimation to accelerate the convergence of QLC.
  arXiv  Detail & Related papers  (2026-02-12T20:30:53Z)
• Decentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking [45.147301546565316]
  This paper considers the problem of decentralized optimization on compact submanifolds.<n>We propose an algorithm where agents update variables using quantized variables.<n>To the best of our knowledge, this is the first algorithm to achieve an $mathcalO (1/K)$ convergence rate in the presence of quantization.
  arXiv  Detail & Related papers  (2025-06-09T01:57:25Z)
• Gradient Normalization Provably Benefits Nonconvex SGD under Heavy-Tailed Noise [60.92029979853314]
  We investigate the roles of gradient normalization and clipping in ensuring the convergence of Gradient Descent (SGD) under heavy-tailed noise. Our work provides the first theoretical evidence demonstrating the benefits of gradient normalization in SGD under heavy-tailed noise. We introduce an accelerated SGD variant incorporating gradient normalization and clipping, further enhancing convergence rates under heavy-tailed noise.
  arXiv  Detail & Related papers  (2024-10-21T22:40:42Z)
• 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)
• Differentiable Annealed Importance Sampling and the Perils of Gradient Noise [68.44523807580438]
  Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation. Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective. We propose a differentiable algorithm by abandoning Metropolis-Hastings steps, which further unlocks mini-batch computation.
  arXiv  Detail & Related papers  (2021-07-21T17:10:14Z)
• Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality [131.45028999325797]
  We develop a doubly robust off-policy AC (DR-Off-PAC) for discounted MDP. DR-Off-PAC adopts a single timescale structure, in which both actor and critics are updated simultaneously with constant stepsize. We study the finite-time convergence rate and characterize the sample complexity for DR-Off-PAC to attain an $epsilon$-accurate optimal policy.
  arXiv  Detail & Related papers  (2021-02-23T18:56:13Z)
• Fast Convergence Algorithm for Analog Federated Learning [30.399830943617772]
  We propose an AirComp-based FedSplit algorithm for efficient analog federated learning over wireless channels. We prove that the proposed algorithm linearly converges to the optimal solutions under the assumption that the objective function is strongly convex and smooth. Our algorithm is theoretically and experimentally verified to be much more robust to the ill-conditioned problems with faster convergence compared with other benchmark FL algorithms.
  arXiv  Detail & Related papers  (2020-10-30T10:59:49Z)
• 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)
• Approximation Algorithms for Sparse Principal Component Analysis [57.5357874512594]
  Principal component analysis (PCA) is a widely used dimension reduction technique in machine learning and statistics. Various approaches to obtain sparse principal direction loadings have been proposed, which are termed Sparse Principal Component Analysis. We present thresholding as a provably accurate, time, approximation algorithm for the SPCA problem.
  arXiv  Detail & Related papers  (2020-06-23T04:25:36Z)
• 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)
• Second-Order Guarantees in Centralized, Federated and Decentralized Nonconvex Optimization [64.26238893241322]
  Simple algorithms have been shown to lead to good empirical results in many contexts. Several works have pursued rigorous analytical justification for studying non optimization problems. A key insight in these analyses is that perturbations play a critical role in allowing local descent algorithms.
  arXiv  Detail & Related papers  (2020-03-31T16:54:22Z)

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.