Distributed Optimization Over Time-Varying Directed Graphs

By Angelia Nedić, Alexander Olshevsky. 2015

353 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

Citations in the corpus

Central Server Free Federated Learning over Single-sided Trust Social Networks (2019, neutral): “, 2018), and time-varying (Nedić and Olshevsky, 2015; Lian et al., 2018) during training.”
GADMM: Fast and Communication Efficient Framework for Distributed Machine Learning (2019, methodology): “On the other hand, there are a variety of distributed optimization algorithms proposed in the literature, such as primal methods (Jakovetić et al., 2014; Nedić and Olshevsky, 2014; Nedić and Ozdaglar, 2009; Shi et al., 2015) and primal-dual methods (Chang et al.”
Network Topology and Communication-Computation Tradeoffs in Decentralized Optimization (2017, methodology): “This Push Sum consensus-based algorithm has been extended to the subgradient-push algorithm in [47], [48] that can deal with convex optimization problems over time-varying directed graphs.”
Distributed Gradient Methods for Convex Machine Learning Problems in Networks: Distributed Optimization (2020, methodology): “Subsequently, in [15] a simple (sub)gradient method using the push–sum consensus has been proposed for a general sequence of time-varying directed graphs and is later extended to a stochastic method in [16].”
Asynchronous Gradient Push (2018, positive): “Nedi´c and Olshevsky [21] continue this line of work by introducing and analyzing the Subgradient-Push method; the analysis in [21] focuses on minimizing (weakly) convex, Lip-schitz functions, for which diminishing step-sizes are required to obtain convergence.”
A Decentralized Proximal-Gradient Method With Network Independent Step-Sizes and Separated Convergence Rates (2017, background): “Another topic of interest is decentralized optimization over directed graphs [41], [43]–[46], which is beyond the scope of this paper.”
A geometrically convergent method for distributed optimization over time-varying graphs (2016, methodology): “references [22]–[26] work with directed graphs.”
Optimization over time-varying directed graphs with row and column-stochastic matrices (2018, methodology): “The performance of TV-AB along with Push-DIGing [26], and subgradientpush [18] (with constant and diminishing step-sizes) is shown in Fig.”
NEXT: In-Network Nonconvex Optimization (2016, methodology): “Algorithms belonging to the former class include: i) consensus-based (sub)gradient schemes [1]–[4] along with their accelerated and asynchronous versions [5]–[7]; ii) the (sub)gradient push-method [8], [9]; iii) the dual-average method [10], [11]; and iv) distributed secondorder-based schemes [12], ”
Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks (2017, background): “Subsequently, many variants of DSG have been proposed, either with special assumptions on the underlying graph, or having additional structures of the problem; see, e.g., (Lobel & Ozdaglar, 2011; Lobel et al., 2011; Nedic & Olshevsky, 2015).”