Zobrazeno 1 - 10
of 2 743
pro vyhledávání: '"Sayed, A. H."'
Autor:
Zhaikhan, Ainur, Sayed, Ali H.
This study proposes the use of a social learning method to estimate a global state within a multi-agent off-policy actor-critic algorithm for reinforcement learning (RL) operating in a partially observable environment. We assume that the network of a
Externí odkaz:
http://arxiv.org/abs/2407.04974
This paper proposes a theoretical framework to evaluate and compare the performance of gradient-descent algorithms for distributed learning in relation to their behavior around local minima in nonconvex environments. Previous works have noticed that
Externí odkaz:
http://arxiv.org/abs/2406.20006
Communication-constrained algorithms for decentralized learning and optimization rely on local updates coupled with the exchange of compressed signals. In this context, differential quantization is an effective technique to mitigate the negative impa
Externí odkaz:
http://arxiv.org/abs/2406.18418
Lower-bound analyses for nonconvex strongly-concave minimax optimization problems have shown that stochastic first-order algorithms require at least $\mathcal{O}(\varepsilon^{-4})$ oracle complexity to find an $\varepsilon$-stationary point. Some wor
Externí odkaz:
http://arxiv.org/abs/2406.13041
In this paper, we consider a setting where heterogeneous agents with connectivity are performing inference using unlabeled streaming data. Observed data are only partially informative about the target variable of interest. In order to overcome the un
Externí odkaz:
http://arxiv.org/abs/2405.01260
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 observations conditioned on the same true state, although it is also
Externí odkaz:
http://arxiv.org/abs/2403.12619
In this work, we examine a network of agents operating asynchronously, aiming to discover an ideal global model that suits individual local datasets. Our assumption is that each agent independently chooses when to participate throughout the algorithm
Externí odkaz:
http://arxiv.org/abs/2402.05529
The optimistic gradient method is useful in addressing minimax optimization problems. Motivated by the observation that the conventional stochastic version suffers from the need for a large batch size on the order of $\mathcal{O}(\varepsilon^{-2})$ t
Externí odkaz:
http://arxiv.org/abs/2401.14585
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, we relax this assumption and study the distributed hypothesis testin
Externí odkaz:
http://arxiv.org/abs/2312.12186
Autor:
Kayaalp, Mert, Sayed, Ali H.
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 and distributed decision-making protocols, and derives expressions th
Externí odkaz:
http://arxiv.org/abs/2307.09575