GT-STORM: Taming Sample, Communication, and Memory Complexities in Decentralized Non-Convex Learning

Abstract

Decentralized nonconvex optimization has received increasing attention in recent years in machine learning due to its advantages in system robustness, data privacy, and implementation simplicity. However, three fundamental challenges in designing decentralized optimization algorithms are how to reduce their sample, communication, and memory complexities. In this paper, we propose a \underline{g}radient-\underline{t}racking-based \underline{sto}chastic \underline{r}ecursive \underline{m}omentum (GT-STORM) algorithm for efficiently solving nonconvex optimization problems. We show that to reach an ${\epsilon }^2$-stationary solution, the total number of sample evaluations of our algorithm is $\tilde{O}(m^{1/2}{\epsilon }^{-3})$ and the number of communication rounds is $\tilde{O}(m^{-1/2}{\epsilon }^{-3})$, which improve the $O({\epsilon }^{-4})$ costs of sample evaluations and communications for the existing decentralized stochastic gradient algorithms. We conduct extensive experiments with a variety of learning models, including non-convex logistical regression and convolutional neural networks, to verify our theoretical findings. Collectively, our results contribute to the state of the art of theories and algorithms for decentralized network optimization.

References in corpus (10)

• Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication
• DSA: Decentralized Double Stochastic Averaging Gradient Algorithm
• Decentralized Quasi-Newton Methods
• Dictionary Learning over Distributed Models
• Distributed Non-Convex First-Order Optimization and Information Processing: Lower Complexity Bounds and Rate Optimal Algorithms
• Distributed Stochastic Multi-Task Learning with Graph Regularization
• Generalization Error Bounds with Probabilistic Guarantee for SGD in Nonconvex Optimization
• Cubic Regularization with Momentum for Nonconvex Optimization
• Variance-Reduced Decentralized Stochastic Optimization with Gradient Tracking--Part I: GT-SAGA
• Distributed Linear Model Clustering over Networks: A Tree-Based Fused-Lasso ADMM Approach