相关论文: Online Learning with Randomized Feedback Graphs fo…

We study the $K$-armed contextual dueling bandit problem, a sequential decision making setting in which the learner uses contextual information to make two decisions, but only observes \emph{preference-based feedback} suggesting that one…

This paper considers an online reinforcement learning algorithm that leverages pre-collected data (passive memory) from the environment for online interaction. We show that using passive memory improves performance and further provide…

In cognitive radio systems, employing sensing-based spectrum access strategies, secondary users are required to perform channel sensing in order to detect the activities of primary users. In realistic scenarios, channel sensing occurs with…

We consider systems that require timely monitoring of sources over a communication network, where the cost of delayed information is unknown, time-varying and possibly adversarial. For the single source monitoring problem, we design…

We investigate a cognitive radio scenario involving a single cognitive transmitter equipped with $\mathcal{K}$ antennas sharing the spectrum with $\mathcal{M}$ primary users (PUs) transmitting over orthogonal bands. Each terminal has a…

The goal of a learner, in standard online learning, is to have the cumulative loss not much larger compared with the best-performing function from some fixed class. Numerous algorithms were shown to have this gap arbitrarily close to zero,…

In a cognitive radio scenario we consider a single secondary user (SU) accessing a multi-channel system. The SU senses the channels sequentially to detect if a primary user (PU) is occupying the channels, and stops its search to access a…

In this paper we study opportunistic transmission strategies for cognitive radios (CR) in which causal noisy observation from a primary user(s) (PU) state is available. PU is assumed to be operating in a slotted manner, according to a…

Powerful spectrum handover schemes enable cognitive radios (CRs) to use transmission opportunities in primary users' channels appropriately. In this paper, we consider the cognitive access of primary channels by a secondary user. We…

We investigate power allocation for users in a spectrum underlay cognitive network. Our objective is to find a power control scheme that allocates transmit power for both primary and secondary users so that the overall network throughput is…

We consider the problem of dynamic spectrum access (DSA) in cognitive wireless networks, where only partial observations are available to the users due to narrowband sensing and transmissions. The cognitive network consists of primary users…

Bandit-style algorithms have been studied extensively in stochastic and adversarial settings. Such algorithms have been shown to be useful in multiplayer settings, e.g. to solve the wireless network selection problem, which can be…

Cognitive (Radio) (CR) Communications (CC) are mainly deployed within the environments of primary (user) communications, where the channel states and accessibility are usually stochastically distributed (benign or IID). However, many…

Cognitive Radio (CR) technology is a solution to solve the lack of spectrum by allowing the secondary user to use licensed bands. There are several potential security challenges for cognitive radio like Jamming, PUE and Lion attack. Lion…

Cognitive radio networks (CRNs) are acknowledged for their ability to tackle the issue of spectrum under-utilization. In the realm of CRNs, this paper investigates the energy efficiency issue and addresses the critical challenge of…

In Cognitive Radio Networks (CRNs), the secondary users (SUs) are allowed to access the licensed channels opportunistically. A fundamental and essential operation for SUs is to establish communication through choosing a common channel at…

Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease a victim's cumulative expected reward by manipulating the victim's observations. Despite the efficiency of previous optimization-based methods for…

We study the problem of learning-based attacks in linear systems, where the communication channel between the controller and the plant can be hijacked by a malicious attacker. We assume the attacker learns the dynamics of the system from…

An underlay cognitive radio network with energy harvesting is considered which operates in slotted fashion. The primary user (PU) transmits with a constant power in each slot, while the secondary user (SU) either harvests energy from…

In this paper, we consider the channel allocation problem for throughput maximization in cognitive radio networks with hardware-constrained secondary users. Specifically, we assume that secondary users exploit spectrum holes on a set of…