Decentralized multi-agent stochastic optimization with pairwise constraints and quantized communications

X Cao, T Başar - IEEE Transactions on Signal Processing, 2020 - ieeexplore.ieee.org
… In Section II, we formulate the multi-agent stochastic optimization problem with quantized
communications. In Section III, we study quantized decentralized stochastic optimization with …

Quantization enabled privacy protection in decentralized stochastic optimization

Y Wang, T Başar - IEEE Transactions on Automatic Control, 2022 - ieeexplore.ieee.org
… of decentralized stochastic optimization. In this paper, we propose a decentralized stochastic
optimization … of aggressive quantization errors that are proportional to the amplitude of …

Decentralized Stochastic Optimization With Pairwise Constraints and Variance Reduction

F Han, X Cao, Y Gong - IEEE Transactions on Signal …, 2024 - ieeexplore.ieee.org
… The impact of quantization on personalized multi-agent decentralized … interested in formulating
multi-agent finite-sum optimization problems with pairwise constraints and introducing the …

Decentralized multi-task stochastic optimization with compressed communications

N Singh, X Cao, S Diggavi, T Başar - Automatica, 2024 - Elsevier
… function subject to all the pairwise constraints. This is to be … the existing works on decentralized
optimization with quantized/… of decentralized multi-agent stochastic optimization on a …

Asynchronous decentralized SGD with quantized and local updates

G Nadiradze, A Sabour, P Davies… - Advances in Neural …, 2021 - proceedings.neurips.cc
Stochastic Optimization. We assume that the agents wish to jointly minimize a d-dimensional,
differentiable function f : Rd → R. Specifically, we will assume the empirical risk …

Decentralized SGD with asynchronous, local and quantized updates

G Nadiradze, A Sabour, P Davies, I Markov, S Li… - 2019 - openreview.net
… local optimization steps, a node can initiate a pairwise interaction with a uniform random
neighbor… Stochastic Optimization. We assume that the agents wish to minimize a d-dimensional, …

Fully decentralized multi-agent reinforcement learning with networked agents

K Zhang, Z Yang, H Liu, T Zhang… - … conference on machine …, 2018 - proceedings.mlr.press
We consider the fully decentralized multi-agent reinforcement learning (MARL) problem, where
the agents are connected via a time-varying and possibly sparse communication network…

Convergence of a multi-agent projected stochastic gradient algorithm for non-convex optimization

P Bianchi, J Jakubowicz - IEEE transactions on automatic …, 2012 - ieeexplore.ieee.org
… We compare the pairwise and the broadcast gossip schemes. Note that we only plot the result
decentralized detection, quantization, stochastic optimization, and applications of random

[PDF][PDF] Decentralization meets quantization

H Tang, C Zhang, S Gan, T Zhang… - arXiv preprint arXiv …, 2018 - researchgate.net
… Fully decentralized policies for multi-agent systems: An information theoretic approach. In
Advances in Neural Information Processing Systems, pages 2945–2954, 2017. …

[PDF][PDF] Decentralized Estimation for Stochastic Multi-agent Systems

FW Shaw - 2012 - digital.lib.washington.edu
… They appear to behave in a decentralized, asynchronous manner yet manage to reach a …
A large group of people can make decisions in a decentralized way to form a pattern. In Fig. …