30 citations · 47 across the 18 of their papers we have counts for
19 papers
Test-Time Collaborative Classification over Multi-Agent Networks
Ping Hu, Mert Kayaalp, Ali H. Sayed
The increasing heterogeneity of multi-agent systems poses significant challenges for jointly training a global model across agents. At the same time, cooperative inference between…
Signal Recovery from Time and Frequency Samples
Mert Kayaalp, Oleg Szehr
We analyze signal recovery when samples are taken concomitantly from a signal and its Fourier transform. This two-sided sampling framework extends classical one-sided reconstructio…
Opinion Consensus Formation Among Networked Large Language Models
Iris Yazici, Mert Kayaalp, Stefan Taga +1
Can classical consensus models predict the group behavior of large language models (LLMs)? We examine multi-round interactions among LLM agents through the DeGroot framework, where…
Test-Time Efficient Pretrained Model Portfolios for Time Series Forecasting
Mert Kayaalp, Caner Turkmen, Oleksandr Shchur +4
Is bigger always better for time series foundation models? With the question in mind, we explore an alternative to training a single, large monolithic model: building a portfolio o…
Causal Influence in Federated Edge Inference
Mert Kayaalp, Yunus Inan, Visa Koivunen +1
In this paper, we consider a setting where heterogeneous agents with connectivity are performing inference using unlabeled streaming data. Observed data are only partially informat…
Detection of Malicious Agents in Social Learning
Valentina Shumovskaia, Mert Kayaalp, Ali H. Sayed
Non-Bayesian social learning is a framework for distributed hypothesis testing aimed at learning the true state of the environment. Traditionally, the agents are assumed to receive…
Social Learning in Community Structured Graphs
Valentina Shumovskaia, Mert Kayaalp, Ali H. Sayed
Traditional social learning frameworks consider environments with a homogeneous state, where each agent receives observations conditioned on that true state of nature. In this work…
Causal Influences over Social Learning Networks
Mert Kayaalp, Ali H. Sayed
This paper investigates causal influences between agents linked by a social graph and interacting over time. In particular, the work examines the dynamics of social learning models…
Non-Asymptotic Performance of Social Machine Learning Under Limited Data
Ping Hu, Virginia Bordignon, Mert Kayaalp +1
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-m…
On the Fusion Strategies for Federated Decision Making
Mert Kayaalp, Yunus Inan, Visa Koivunen +2
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 p…
Policy Evaluation in Decentralized POMDPs with Belief Sharing
Mert Kayaalp, Fatima Ghadieh, Ali H. Sayed
Most works on multi-agent reinforcement learning focus on scenarios where the state of the environment is fully observable. In this work, we consider a cooperative policy evaluatio…
Distributed Bayesian Learning of Dynamic States
Mert Kayaalp, Virginia Bordignon, Stefan Vlaski +2
This work studies networked agents cooperating to track a dynamical state of nature under partial information. The proposed algorithm is a distributed Bayesian filtering algorithm…
Discovering Influencers in Opinion Formation over Social Graphs
Valentina Shumovskaia, Mert Kayaalp, Mert Cemri +1
The adaptive social learning paradigm helps model how networked agents are able to form opinions on a state of nature and track its drifts in a changing environment. In this framew…
A Fundamental Limit of Distributed Hypothesis Testing Under Memoryless Quantization
Yunus Inan, Mert Kayaalp, Ali H. Sayed +1
We study a distributed hypothesis testing setup where peripheral nodes send quantized data to the fusion center in a memoryless fashion. The \emph{expected} number of bits sent by…
On the Arithmetic and Geometric Fusion of Beliefs for Distributed Inference
Mert Kayaalp, Yunus Inan, Emre Telatar +1
We study the asymptotic learning rates under linear and log-linear combination rules of belief vectors in a distributed hypothesis testing problem. We show that under both combinat…
Social Opinion Formation and Decision Making Under Communication Trends
Mert Kayaalp, Virginia Bordignon, Ali H. Sayed
This work studies the learning process over social networks under partial and random information sharing. In traditional social learning models, agents exchange full belief informa…
Social Learning under Randomized Collaborations
Yunus Inan, Mert Kayaalp, Emre Telatar +1
We study a social learning scheme where at every time instant, each agent chooses to receive information from one of its neighbors at random. We show that under this sparser commun…
Hidden Markov Modeling over Graphs
Mert Kayaalp, Virginia Bordignon, Stefan Vlaski +1
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 opi…
Dif-MAML: Decentralized Multi-Agent Meta-Learning
Mert Kayaalp, Stefan Vlaski, Ali H. Sayed
The objective of meta-learning is to exploit the knowledge obtained from observed tasks to improve adaptation to unseen tasks. As such, meta-learners are able to generalize better…