A novel computation-efficient quantized distributed optimization algorithm is presented in this article for solving a class of convex optimization problems over time-varying undirected networks with limited communicat...
详细信息
A novel computation-efficient quantized distributed optimization algorithm is presented in this article for solving a class of convex optimization problems over time-varying undirected networks with limited communication capacity. These convex optimization problems are usually relevant to the minimization of a sum of local convex objective functions using only local communication and local computation. In most of the existing distributed optimization algorithms, each agent needs to calculate the subgradient of its local convex objective function at each time step, which leads to extremely heavy computation. The proposed algorithm incorporates random sleep scheme into procedures of agents' updates in a probabilistic form to reduce the computation load, and further allows for uncoordinated step-sizes of all agents. The quantized strategy is also applied, which overcomes the limitation of communication capacity. Theoretical analysis indicates that the convex optimization problems can be solved and numerical analysis shows that the computation load of subgradient can be significantly reduced by the proposed algorithm. The boundedness of the quantization levels at each time step has been explicitly characterized. Simulation examples are presented to demonstrate the effectiveness of the algorithm and the correctness of the theoretical results.
efficient key establishment is an important problem for secure group communications. The communication and storage complexity of group key establishment problem has been studied extensively. In this paper, we propose ...
详细信息
efficient key establishment is an important problem for secure group communications. The communication and storage complexity of group key establishment problem has been studied extensively. In this paper, we propose a new group key establishment protocol whose computation complexity is significantly reduced. Instead of using classic secret sharing, the protocol only employs a linear secret sharing scheme, using Vandermonde Matrix, to distribute group key efficiently. This protocol drastically reduces the computation load of each group member and maintains at least the same security degree compared to existing schemes employing traditional secret sharing. The security strength of this scheme is evaluated in detail. Such a protocol is desirable for many wireless applications where portable devices or sensors need to reduce their computation as much as possible due to battery power limitations. This protocol provides much lower computation complexity while maintaining low and balanced communication complexity and storage complexity for secure group key establishment.
This paper focuses on solving the problem of composite constrained convex optimization with a sum of smooth convex functions and non-smooth regularization terms (l(1) norm) subject to locally general constraints. Moti...
详细信息
This paper focuses on solving the problem of composite constrained convex optimization with a sum of smooth convex functions and non-smooth regularization terms (l(1) norm) subject to locally general constraints. Motivated by the modern large-scale information processing problems in machine learning (the samples of a training dataset are randomly decentralized across multiple computing nodes), each of the smooth objective functions is further considered as the average of several constituent functions. To address the problem in a decentralized fashion, we propose a novel computation-efficient decentralized stochastic gradient algorithm, which leverages the variance reduction technique and the decentralized stochastic gradient projection method with constant step-size. Theoretical analysis indicates that if the constant step-size is less than an explicitly estimated upper bound, the proposed algorithm can find the exact optimal solution in expectation when each constituent function (smooth) is strongly convex. Concerning the existing decentralized schemes, the proposed algorithm not only is suitable for solving the general constrained optimization problems but also possesses low computation cost in terms of the total number of local gradient evaluations. Furthermore, the proposed algorithm via differential privacy strategy can effectively mask the privacy of each constituent function, which is more practical in applications involving sensitive messages, such as military affairs or medical treatment. Finally, numerical evidence is provided to demonstrate the appealing performance of the proposed algorithm.
Voice activity detection serves as an essential preprocessor in modern speech processing systems. It classifies audio segments into speech and nonspeech. Many state-of-the-art methods have been proposed to increase th...
详细信息
ISBN:
(纸本)9789082797091
Voice activity detection serves as an essential preprocessor in modern speech processing systems. It classifies audio segments into speech and nonspeech. Many state-of-the-art methods have been proposed to increase the detection accuracy. However, there are still significant limitations to retaining high performance while keeping low computation complexity, especially in handling unseen noises. This paper proposes a computation-efficient neural network using a multi-channel audio feature. The audio feature is contextual-aware with positional information and is represented in a three-channel way, similar to RGB pictures, which enables convolutional kernels to capture more information simultaneously. Meanwhile, we introduce channel attention inverted blocks to build a computation-efficient neural network. Our proposed method shows superior performance with extremely few floating point operations as compared with baseline methods.
Agriculture is the golden thread that fastens all the sustainable development goals globally. However, the massive population explosion and ecosystem degradation have pressurized various auxiliaries of agriculture, pr...
详细信息
Agriculture is the golden thread that fastens all the sustainable development goals globally. However, the massive population explosion and ecosystem degradation have pressurized various auxiliaries of agriculture, primarily food security, crop protection, and disease identification. Although the penetration of digital technologies brings new opportunities to modern agriculture, the environmental facet has been neglected. Given this, the potential of sustainable computing and deep learning is investigated to handle critical agricultural technology impediments, lower resource expenditure, and propel sustainable agrarian developments. This research analyzes the relationship between Smart Agriculture and Sustainable Computing to balance the three pillars of Sustainable Agriculture practices-socio-economic-environment. Motivated by the analysis, the proposed work presents a deep learning-based lightweight, computation-efficient, performance-optimized, and explainable crop protection model to classify plant diseases. The proposed model reports accuracy, precision, recall, and F1-score of 99.4%, 99.4%, 99.5%, and 99.6%, respectively, outperforming state-of-the-art models. Further, the F1-score is improved by 15%, using 6.29 x fewer trainable parameters and 1.88 x fewer FLOPs that facilitate seamless deployment of the model on embedded devices, particularly for automated in situ plant disease classification. Moreover, to confirm the applicability of the proposed model across various crops, validation is conducted on additional crops, showcasing the model's efficacy. The proposed model serves as a sustainable and innovative technological solution, aiding in the preservation of agricultural yields, enhancement of quality, and reduction of pesticide usage to safeguard the environment, achieved through energy-efficient resource utilization.
暂无评论