Distributed dual averaging method for multi-agent optimization with quantized communication

By Deming Yuan, Shengyuan Xu, Huanyu Zhao, Lina Rong. 2012

91 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Networks and Communications

Citations in the corpus

Decentralized Deep Learning with Arbitrary Communication Compression (2019, background): “It has been observed that gossip averaging can diverge (or not converge to the correct solution) in the presence of quantization noise (Xiao et al., 2005; Carli et al., 2007; Nedić et al., 2008; Dimakis et al., 2010; Carli et al., 2010b; Yuan et al., 2012).”
Decentralized Stochastic Optimization and Gossip Algorithms with Compressed Communication (2019, methodology): “The proposed schemes in (Carli et al., 2007; Nedi´c et al., 2008; Aysal et al., 2008; Carli et al., 2010b; Yuan et al., 2012) do only converge to a neighborhood (whose size depends on the compression accuracy) of the solution.”
Gossip Dual Averaging for Decentralized Optimization of Pairwise Functions (2016, neutral): “…& Ozdaglar, 2009; Ram et al., 2010; Bianchi & Jakubow-icz, 2013), ADMM (Wei & Ozdaglar, 2012; 2013; Iutzeler et al., 2013) or dual averaging (Duchi et al., 2012; Yuan et al., 2012; Lee et al., 2015; Tsianos et al., 2015), some of which can also accommodate constraints or regularization on θ .”
Quantized consensus ADMM for multi-agent distributed optimization (2015, methodology): “Methods that handle this constraint include quantized incremental algorithm [21], quantized dual averaging [22], and quantized subgradient method [16].”
Convergence Analysis of Quantized Primal-Dual Algorithms in Network Utility Maximization Problems (2016, background): “[6] considered a constrained optimization problem in which a group of agents cooperate to minimize the sum of their local convex objective functions subject to a set of global constraints.”
Nested Distributed Gradient Methods with Adaptive Quantized Communication (2019, methodology): “and local information [13], [18], [21], designing custom quantizers [12], [14], [26] and employing encoding/decoding schemes to alleviate communication load [18], [19], [27].”