Extrapolation-based Prediction-Correction Methods for Time-varying Convex Optimization
arXiv:2004.11709 · doi:10.1016/j.sigpro.2023.109089
Abstract
In this paper, we focus on the solution of online optimization problems that arise often in signal processing and machine learning, in which we have access to streaming sources of data. We discuss algorithms for online optimization based on the prediction-correction paradigm, both in the primal and dual space. In particular, we leverage the typical regularized least-squares structure appearing in many signal processing problems to propose a novel and tailored prediction strategy, which we call extrapolation-based. By using tools from operator theory, we then analyze the convergence of the proposed methods as applied both to primal and dual problems, deriving an explicit bound for the tracking error, that is, the distance from the time-varying optimal solution. We further discuss the empirical performance of the algorithm when applied to signal processing, machine learning, and robotics problems.
arXiv commentTo be published in Elsevier Signal Processing
References in corpus (9)
- A Class of Prediction-Correction Methods for Time-Varying Convex Optimization
- Online Learning with Inexact Proximal Online Gradient Descent Algorithms
- Prediction-Correction Algorithms for Time-Varying Constrained Optimization
- Asynchronous Distributed Optimization over Lossy Networks via Relaxed ADMM: Stability and Linear Convergence
- Recursive Recovery of Sparse Signal Sequences from Compressive Measurements: A Review
- Optimization and Learning with Information Streams: Time-varying Algorithms and Applications
- Dynamic Filtering of Time-Varying Sparse Signals via l1 Minimization
- Discrete and Continuous-time Soft-Thresholding with Dynamic Inputs
- An Online Parallel and Distributed Algorithm for Recursive Estimation of Sparse Signals