W
Wei Shi
Researcher at Arizona State University
Publications - 57
Citations - 6515
Wei Shi is an academic researcher from Arizona State University. The author has contributed to research in topics: Optimization problem & Rate of convergence. The author has an hindex of 25, co-authored 56 publications receiving 4711 citations. Previous affiliations of Wei Shi include Boston University & Princeton University.
Papers
More filters
Journal ArticleDOI
EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization
TL;DR: A novel decentralized exact first-order algorithm (abbreviated as EXTRA) to solve the consensus optimization problem and uses a fixed, large step size, which can be determined independently of the network size or topology.
Journal ArticleDOI
On the Linear Convergence of the ADMM in Decentralized Consensus Optimization
TL;DR: This paper establishes its linear convergence rate for the decentralized consensus optimization problem with strongly convex local objective functions in terms of the network topology, the properties ofLocal objective functions, and the algorithm parameter.
Journal ArticleDOI
Achieving Geometric Convergence for Distributed Optimization Over Time-Varying Graphs
TL;DR: This paper introduces a distributed algorithm, referred to as DIGing, based on a combination of a distributed inexact gradient method and a gradient tracking technique that converges to a global and consensual minimizer over time-varying graphs.
Posted Content
EXTRA: An Exact First-Order Algorithm for Decentralized Consensus Optimization
TL;DR: In this paper, a decentralized algorithm called EXTRA was proposed to solve the consensus optimization problem in a multi-agent network, where each function is held privately by an agent and the objective function is shared among all the agents.
Journal ArticleDOI
Federated learning of predictive models from federated Electronic Health Records.
Theodora S. Brisimi,Ruidi Chen,Theofanie Mela,Alex Olshevsky,Ioannis Ch. Paschalidis,Wei Shi +5 more
TL;DR: An iterative cluster Primal Dual Splitting algorithm for solving the large-scale sSVM problem in a decentralized fashion, which extracts important features discovered by the algorithm that are predictive of future hospitalizations, thus providing a way to interpret the classification results and inform prevention efforts.