Improved Analysis of the Accelerated Noisy Power Method with Applications to Decentralized PCA
Researchers have developed an improved analysis for the Accelerated Noisy Power Method, an algorithm used in decentralized Principal Component Analysis (PCA). This new analysis relaxes the strict upper bounds on perturbation magnitudes previously required for accelerated convergence. The findings demonstrate that the derived convergence rate is worst-case optimal and establish the first decentralized PCA algorithm with provably accelerated convergence, maintaining similar communication costs to non-accelerated methods. AI
IMPACT Provides a theoretical advancement for decentralized machine learning algorithms, potentially improving efficiency in distributed data analysis.