no code implementations • 13 Jul 2023 • Mert Kayaalp, Ali H. Sayed
This paper investigates causal influences between agents linked by a social graph and interacting over time.
no code implementations • 15 Jun 2023 • Ping Hu, Virginia Bordignon, Mert Kayaalp, Ali H. Sayed
This paper studies the probability of error associated with the social machine learning framework, which involves an independent training phase followed by a cooperative decision-making phase over a graph.
no code implementations • 10 Mar 2023 • Mert Kayaalp, Yunus Inan, Visa Koivunen, Emre Telatar, Ali H. Sayed
We consider the problem of information aggregation in federated decision making, where a group of agents collaborate to infer the underlying state of nature without sharing their private data with the central processor or each other.
1 code implementation • 8 Feb 2023 • Mert Kayaalp, Fatima Ghadieh, Ali H. Sayed
As a remedy, we propose a fully decentralized belief forming strategy that relies on individual updates and on localized interactions over a communication network.
no code implementations • 5 Dec 2022 • Mert Kayaalp, Virginia Bordignon, Stefan Vlaski, Vincenzo Matta, Ali H. Sayed
This work studies networked agents cooperating to track a dynamical state of nature under partial information.
no code implementations • 28 Apr 2022 • Mert Kayaalp, Yunus Inan, Emre Telatar, Ali H. Sayed
We study the asymptotic learning rates under linear and log-linear combination rules of belief vectors in a distributed hypothesis testing problem.
no code implementations • 4 Mar 2022 • Mert Kayaalp, Virginia Bordignon, Ali H. Sayed
We show that agents can learn the true hypothesis even if they do not discuss it, at rates comparable to traditional social learning.
no code implementations • 26 Nov 2021 • Mert Kayaalp, Virginia Bordignon, Stefan Vlaski, Ali H. Sayed
This work proposes a multi-agent filtering algorithm over graphs for finite-state hidden Markov models (HMMs), which can be used for sequential state estimation or for tracking opinion formation over dynamic social networks.
no code implementations • 6 Oct 2020 • Mert Kayaalp, Stefan Vlaski, Ali H. Sayed
The formalism of meta-learning is actually well-suited to this decentralized setting, where the learner would be able to benefit from information and computational power spread across the agents.