Search

Multi-kernel learning (MKL) has been widely used in learning problems involving function learning tasks. Compared with single kernel learning approach which relies on a pre-selected kernel, the advantage of MKL is its flexibility results from combining a dictionary of kernels. However, inclusion of irrelevant kernels in the dictionary may deteriorate the accuracy of MKL, and increase the computational complexity. Faced with this challenge, a novel graph-aided framework is developed to select a subset of kernels from the dictionary with the assistance of a graph. Different graph construction and refinement schemes are developed based on incurred losses or kernel similarities to assist the adaptive selection process. Moreover, to cope with the scenario where data may be collected in a sequential fashion, or cannot be stored in batch due to the massive scale, random feature approximation are adopted to enable online function learning. It is proved that our proposed algorithms enjoy sub-linear regret bounds. Experiments on a number of real datasets showcase the advantages of our novel graph-aided algorithms compared to state-of-the-art alternatives. 1 [ABSTRACT FROM AUTHOR]

To provide effective wireless connectivity, the use of aerial vehicles has been proposed as a promising solution in a wide variety of applications. In some of these applications, however, to achieve desirable performance, knowing the location of users may be a necessity. One promising approach for solving the problem of obtaining user locations is through the locations of some nodes (called anchors) and measuring the distance between connected nodes in the network. In this paper, we propose prominent techniques to improve the performance of the localization using multiple moving aerial anchors (MAA). In using MAAs as anchor nodes, the anchor nodes in our scenario have movement capability. This provides us with more flexibility to enhance the accuracy of the localization with taking into consideration the power consumption of MAAs. In fact, we propose an MAA placement method by which each user can be connected to at least one MAA while MAAs communicate with as small as possible power consumption. Then, we propose a path planning for MAAs by which distances between users and MAAs can be measured in order to estimate the locations of users. Our simulation results show that our proposed localization scheme can provide highly accurate location estimations. [ABSTRACT FROM AUTHOR]

Providing higher data rate is a momentous goal for wireless communications systems, while interference is an important obstacle to reach this purpose. To cope with this problem, interference alignment (IA) has been proposed. In this paper, we propose two rank minimization methods to enhance the performance of IA in the presence of uncoordinated interference, i.e., interference that cannot be properly aligned with the rest of the network and thus is a crucial issue. In this scenario, perfect and imperfect channel state information (CSI) cases are considered. Our proposed approaches employ the $l_{2}$ and the Schatten- $p$ norms to approximate the rank function, due to its non-convexity. Also, we propose a new convex relaxation to expand the feasible set of our optimization problem, providing lower rank solutions compared to other IA methods from the literature. In addition, we propose a modified weighted-sum method to deal with interference in the relay-aided MIMO interference channel, which employs a set of weighting parameters in order to find more solutions. [ABSTRACT FROM AUTHOR]

The accuracy of localization in wireless sensor networks depends on noise level and the presence of nonline of sight (NLOS) connections. In this letter, we propose a novel semidefinite programming (SDP) method to improve the accuracy and to reduce the required time for wireless sensor network localization in harsh environments. In fact, we perturb Edge-based SDP (ESDP) relaxation and add some constraints to the optimization problem in order to make the proposed localization method robust against large amounts of error in distance measurements. Simulation results confirm that our proposed method outperforms others when the majority of connections are NLOS, noise level is high and it is not possible to distinguish between NLOS and line of sight (LOS) connections. [ABSTRACT FROM PUBLISHER]

Online learning with expert advice is widely used in various machine learning tasks. It considers the problem where a learner chooses one from a set of experts to take advice and make a decision. In many learning problems, experts may be related, henceforth the learner can observe the losses associated with a subset of experts that are related to the chosen one. In this context, the relationship among experts can be captured by a feedback graph, which can be used to assist the learner's decision-making. However, in practice, the nominal feedback graph often entails uncertainties, which renders it impossible to reveal the actual relationship among experts. To cope with this challenge, the present work studies various cases of potential uncertainties and develops novel online learning algorithms to deal with uncertainties while making use of the uncertain feedback graph. The proposed algorithms are proved to enjoy sublinear regret under mild conditions. Experiments on real datasets are presented to demonstrate the effectiveness of the novel algorithms.