Reaching Consensus With Increasing Information

Molavi, Pooya; Jadbabaie, Ali; Rad, Kamiar Rahnama; Tahbaz-Salehi, Alireza

doi:10.1109/jstsp.2013.2246764

Cited by 28 publications

(25 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We believe that a result of this flavor is missing in the existing literature on distributed hypothesis testing, where strong-connectivity is a standard assumption. The authors in [24] do relax the strong-connectivity assumption, but require every strongly-connected component of G to be globally identifiable for learning to take place [24,Proposition 4]. In contrast, Theorem 3 requires only the source components of G to satisfy the global identifiability requirement.…”

Section: Discussion Of the Resultsmentioning

confidence: 99%

A New Approach for Distributed Hypothesis Testing with Extensions to Byzantine-Resilience

Mitra¹,

Richards

Sundaram³

2019

2019 American Control Conference (ACC)

View full text Add to dashboard Cite

We study a setting where a group of agents, each receiving partially informative private signals, seek to collaboratively learn the true underlying state of the world (from a finite set of hypotheses) that generates their joint observation profiles. To solve this problem, we propose a distributed learning rule that differs fundamentally from existing approaches, in that it does not employ any form of "belief-averaging". Instead, agents update their beliefs based on a min-rule. Under standard assumptions on the observation model and the network structure, we establish that each agent learns the truth asymptotically almost surely. As our main contribution, we prove that with probability 1, each false hypothesis is ruled out by every agent exponentially fast at a network-independent rate that is strictly larger than existing rates. We then develop a computationally-efficient variant of our learning rule that is provably resilient to agents who do not behave as expected (as represented by a Byzantine adversary model) and deliberately try to spread misinformation.

show abstract

Section: Discussion Of the Resultsmentioning

confidence: 99%

A New Approach for Distributed Hypothesis Testing with Extensions to Byzantine-Resilience

Mitra¹,

Richards

Sundaram³

2019

2019 American Control Conference (ACC)

View full text Add to dashboard Cite

show abstract

“…Multi-agent models of opinion formation are used to investigate many collective phenomena in social networks, such as the formation of consensus12345, information spreading and aggregating678, and wisdom of crowds910. An opinion formation model generally contains two aspects: an opinion updating rule and an underlying social structure.…”

mentioning

confidence: 99%

Opinion dynamics with similarity-based random neighbors

Liu

Wang

2013

Sci Rep

View full text Add to dashboard Cite

A typical assumption made in the existing opinion formation models is that two individuals can communicate with each other only if the distance between their opinions is less than a threshold called bound of confidence. However, in the real world it is quite possible that people may also have a few friends with quite different opinions. To model this situation, we propose a bounded confidence plus random selection model, in which each agent has several long-range neighbors outside the bound who are selected according to a similarity-based probability rule. We find that the opinions of all agents can reach a consensus in bounded time. We further consider the situation when agents ignore the bound of confidence and select all their neighbors randomly according to the similarity-based probability rule. We prove that in this scenario the whole group could also reach a consensus but in the probability sense.

show abstract

“…This work is also related to a different strand of literature on social learning [12][13] [14][15] and consensus/gossip/diffusion algorithms [16] [17][18] [19]. Networks in these works are exogenously determined.…”

Section: Related Workmentioning

confidence: 99%

Network evolution with incomplete information and learning

Xu¹,

Zhang²,

Schaar³

2014

2014 52nd Annual Allerton Conference on Communication, Control, and Computing (Allerton)

View full text Add to dashboard Cite

We analyze networks that feature reputational learning: how links are initially formed by agents under incomplete information, how agents learn about their neighbors through these links, and how links may ultimately become broken. We show that the type of information agents have access to, and the speed at which agents learn about each other, can have tremendous repercussions for the network evolution and the overall network social welfare. Specifically, faster learning can often be harmful for networks as a whole if agents are myopic, because agents fail to fully internalize the benefits of experimentation and break off links too quickly. As a result, preventing two agents from linking with each other can be socially beneficial, even if the two agents are initially believed to be of high quality. This is due to the fact that having fewer connections slows the rate of learning about these agents, which can be socially beneficial. Another method of solving the informational problem is to impose costs for breaking links, in order to incentivize agents to experiment more carefully.

show abstract

Reaching Consensus With Increasing Information

Cited by 28 publications

References 18 publications

A New Approach for Distributed Hypothesis Testing with Extensions to Byzantine-Resilience

A New Approach for Distributed Hypothesis Testing with Extensions to Byzantine-Resilience

Opinion dynamics with similarity-based random neighbors

Network evolution with incomplete information and learning

Contact Info

Product

Resources

About