Distributed optimization for control

A Nedić, J Liu - Annual Review of Control, Robotics, and …, 2018‏ - annualreviews.org
Advances in wired and wireless technology have necessitated the development of theory,
models, and tools to cope with the new challenges posed by large-scale control and …

Peer-to-peer federated learning on graphs

A Lalitha, OC Kilinc, T Javidi, F Koushanfar - arxiv preprint arxiv …, 2019‏ - arxiv.org
We consider the problem of training a machine learning model over a network of nodes in a
fully decentralized framework. The nodes take a Bayesian-like approach via the introduction …

[PDF][PDF] Fully decentralized federated learning

A Lalitha, S Shekhar, T Javidi… - Third workshop on …, 2018‏ - bayesiandeeplearning.org
We consider the problem of training a machine learning model over a network of users in a
fully decentralized framework. The users take a Bayesian-like approach via the introduction …

Fast convergence rates for distributed non-Bayesian learning

A Nedić, A Olshevsky, CA Uribe - IEEE Transactions on …, 2017‏ - ieeexplore.ieee.org
We consider the problem of distributed learning, where a network of agents collectively aim
to agree on a hypothesis that best explains a set of distributed observations of conditionally …

Geometrically convergent distributed optimization with uncoordinated step-sizes

A Nedić, A Olshevsky, W Shi… - 2017 American Control …, 2017‏ - ieeexplore.ieee.org
A recent algorithmic family for distributed optimization, DIGing's, have been shown to have
geometric convergence over time-varying undirected/directed graphs [1]. Nevertheless, an …

Social learning and distributed hypothesis testing

A Lalitha, T Javidi, AD Sarwate - IEEE Transactions on …, 2018‏ - ieeexplore.ieee.org
This paper considers a problem of distributed hypothesis testing over a network. Individual
nodes in a network receive noisy local (private) observations whose distribution is …

Multi-armed bandits in multi-agent networks

S Shahrampour, A Rakhlin… - 2017 IEEE International …, 2017‏ - ieeexplore.ieee.org
This paper addresses the multi-armed bandit problem in a multi-player framework. Players
explore a finite set of arms with stochastic rewards, and the reward distribution of each arm …

A tutorial on distributed (non-bayesian) learning: Problem, algorithms and results

A Nedić, A Olshevsky, CA Uribe - 2016 IEEE 55th Conference …, 2016‏ - ieeexplore.ieee.org
We overview some results on distributed learning with focus on a family of recently proposed
algorithms known as non-Bayesian social learning. We consider different approaches to the …

Convergence rate of distributed averaging dynamics and optimization in networks

A Nedich - Foundations and Trends® in Systems and …, 2015‏ - nowpublishers.com
Recent advances in wired and wireless technology lead to the emergence of large-scale
networks such as Internet, wireless mobile ad-hoc networks, swarm robotics, smart-grid, and …

Distributed consensus optimization in multiagent networks with time-varying directed topologies and quantized communication

H Li, C Huang, G Chen, X Liao… - IEEE transactions on …, 2017‏ - ieeexplore.ieee.org
This paper considers solving a class of optimization problems which are modeled as the
sum of all agents' convex cost functions and each agent is only accessible to its individual …