Deep reinforcement learning for adaptive caching in hierarchical content delivery networks

A Sadeghi, G Wang… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Caching is envisioned to play a critical role in next-generation content delivery infrastructure,
cellular networks, and Internet architectures. By smartly storing the most popular contents at …

Linear bandits with stochastic delayed feedback

C Vernade, A Carpentier, T Lattimore… - International …, 2020 - proceedings.mlr.press
Stochastic linear bandits are a natural and well-studied model for structured exploration/
exploitation problems and are widely used in applications such as on-line marketing and …

Nonstochastic multiarmed bandits with unrestricted delays

TS Thune, N Cesa-Bianchi… - Advances in Neural …, 2019 - proceedings.neurips.cc
We investigate multiarmed bandits with delayed feedback, where the delays need neither be
identical nor bounded. We first prove that" delayed" Exp3 achieves the $ O (\sqrt {(KT+ D)\ln …

Bayesian optimization under stochastic delayed feedback

A Verma, Z Dai, BKH Low - International Conference on …, 2022 - proceedings.mlr.press
Bayesian optimization (BO) is a widely-used sequential method for zeroth-order optimization
of complex and expensive-to-compute black-box functions. The existing BO methods …

Decentralized online convex optimization with feedback delays

X Cao, T Başar - IEEE Transactions on Automatic Control, 2021 - ieeexplore.ieee.org
In online decision making, feedback delays often arise due to the latency caused by
computation and communication in practical systems. In this article, we study decentralized …

Multi-agent online optimization with delays: Asynchronicity, adaptivity, and optimism

YG Hsieh, F Iutzeler, J Malick… - Journal of Machine …, 2022 - jmlr.org
In this paper, we provide a general framework for studying multi-agent online learning
problems in the presence of delays and asynchronicities. Specifically, we propose and …

Distributed energy resource management: All-time resource-demand feasibility, delay-tolerance, nonlinearity, and beyond

M Doostmohammadian - IEEE Control Systems Letters, 2023 - ieeexplore.ieee.org
In this letter, we propose distributed and networked energy management scenarios to
optimize the production and reservation of energy among a set of distributed energy nodes …

Event-triggered distributed online convex optimization with delayed bandit feedback

M Xiong, B Zhang, D Yuan, Y Zhang, J Chen - Applied Mathematics and …, 2023 - Elsevier
This paper is concerned with an online distributed convex-constrained optimization problem
over a multi-agent network, where the limited network bandwidth and potential feedback …

Delay and cooperation in nonstochastic linear bandits

S Ito, D Hatano, H Sumita… - Advances in …, 2020 - proceedings.neurips.cc
This paper offers a nearly optimal algorithm for online linear optimization with delayed
bandit feedback. Online linear optimization with bandit feedback, or nonstochastic linear …

Secure mobile edge computing in IoT via collaborative online learning

B Li, T Chen, GB Giannakis - IEEE Transactions on Signal …, 2019 - ieeexplore.ieee.org
To accommodate heterogeneous tasks for the Internet of Things (IoT), the emerging mobile
edge paradigm extends computing services from the cloud to the edge, but at the same time …