Distributed and Inexact Proximal Gradient Method for Online Convex Optimization

Abstract

This paper develops and analyzes an online distributed proximal-gradient method (DPGM) for time-varying composite convex optimization problems. Each node of the network features a local cost that includes a smooth strongly convex function and a non-smooth convex function, both changing over time. By coordinating through a connected communication network, the nodes collaboratively track the trajectory of the minimizers without exchanging their local cost functions. The DPGM is implemented in an online fashion, that is, in a setting where only a limited number of steps are implemented before the function changes. Moreover, the algorithm is analyzed in an inexact scenario, that is, with a source of additive noise, that can represent e.g. communication noise or quantization. It is shown that the tracking error of the online inexact DPGM is upper-bounded by a convergent linear system, guaranteeing convergence within a neighborhood of the optimal solution.

To be presented at the European Control Conference 2021 (ECC'21)

References in corpus (18)

• A decentralized proximal-gradient method with network independent step-sizes and separated convergence rates
• Distributed reactive power feedback control for voltage regulation and loss minimization
• Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization
• Online Distributed Optimization on Dynamic Networks
• An Exact Quantized Decentralized Gradient Descent Algorithm
• Online Primal-Dual Methods with Measurement Feedback for Time-Varying Convex Optimization
• Online Learning with Inexact Proximal Online Gradient Descent Algorithms
• The proximal augmented Lagrangian method for nonsmooth composite optimization
• Distributed Algorithms for Composite Optimization: Unified Framework and Convergence Analysis
• Optimization and Learning with Information Streams: Time-varying Algorithms and Applications
• On Maintaining Linear Convergence of Distributed Learning and Optimization under Limited Communication
• Analysis of Distributed ADMM Algorithm for Consensus Optimization in Presence of Node Error
• Zeroth Order Nonconvex Multi-Agent Optimization over Networks
• Can Primal Methods Outperform Primal-dual Methods in Decentralized Dynamic Optimization?
• An Asynchronous Distributed Proximal Gradient Method for Composite Convex Optimization
• Distributed Online Convex Optimization with Improved Dynamic Regret
• A Prediction-Correction Algorithm for Real-Time Model Predictive Control
• Principled Analyses and Design of First-Order Methods with Inexact Proximal Operators

Cited by in corpus (3)

• Robust Online Learning over Networks
• tvopt: A Python Framework for Time-Varying Optimization
• Online Distributed Learning with Quantized Finite-Time Coordination