Randomized Block Proximal Methods for Distributed Stochastic Big-Data Optimization
From MaRDI portal
Abstract: In this paper we introduce a class of novel distributed algorithms for solving stochastic big-data convex optimization problems over directed graphs. In the addressed set-up, the dimension of the decision variable can be extremely high and the objective function can be nonsmooth. The general algorithm consists of two main steps: a consensus step and an update on a single block of the optimization variable, which is then broadcast to neighbors. Three special instances of the proposed method, involving particular problem structures, are then presented. In the general case, the convergence of a dynamic consensus algorithm over random row stochastic matrices is shown. Then, the convergence of the proposed algorithm to the optimal cost is proven in expected value. Exact convergence is achieved when using diminishing (local) stepsizes, while approximate convergence is attained when constant stepsizes are employed. The convergence rate is shown to be sublinear and an explicit rate is provided in the case of constant stepsizes. Finally, the algorithm is tested on a distributed classification problem, first on synthetic data and, then, on a real, high-dimensional, text dataset.
Cited in
(5)- Projected subgradient based distributed convex optimization with transmission noises
- Randomized primal-dual proximal block coordinate updates
- Random block coordinate descent methods for linearly constrained optimization over networks
- Distributed statistical optimization for non-randomly stored big data with application to penalized learning
- A trust‐based resilient consensus algorithm for distributed optimization considering node and edge attacks
This page was built for publication: Randomized Block Proximal Methods for Distributed Stochastic Big-Data Optimization
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4957692)
