An accelerator for support vector machines based on the local geometrical information and data partition

Song, Yunsheng; Liang, Jiye; Wang, Feng

doi:10.1007/s13042-018-0877-7

Cited by 7 publications

(5 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the feasibility of the proposed PSVM-MR algorithm, at the analysis stage, the experiments were conducted using four different datasets, namely ijcnn1, webspam, adult, and kddcup99. The speed-up ratio of the PSVM-MR algorithm on the four datasets is shown in The running times of our proposed PSVM-MR, L-SVM [12], DC-SVM [10], SVM-SMO-SGD [15], DQLS-SVM and IRWLS-SVM [13] on the Ijcnn1, Adult, Web-spam, and Kddcup99 datasets are presented in Fig. 6.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

See 1 more Smart Citation

PSVM-MR: A Parallel Support Vector Machine Algorithm Based on MapReduce

Mao,

Neelakandan

et al. 2024

Preprint

View full text Add to dashboard Cite

In big data environments,utilizing a parallel Support Vector Machine (SVM) can significantly expedite the training process. However, prior efforts have faced challenges due to the excessive deviation of subset distribution, inadequate performance of parallel training, and poor filtering ability of non-support vector. To tackle these obstacles, this paper proposes a novel approach called SVM algorithm based on MapReduce (PSVM-MR). Firstly, a data partition method based on relative entropy (DP-RE) calculates relative entropy to prevent excessive deviation of subset distribution introduced. Secondly, it presents a redundancy level-removing method based on cosine similarity (RLR-CS) that addresses the inadequate performance of parallel training by eliminating the redundancy levels in the cascade structure. Finally, a non-support vector filtering method (NSVF) that enhances the ability of non-support vector filtering by combining rough identification and singular vector identification is proposed. The proposed algorithm demonstrates higher parallel efficiency and lower training costs compared to the general parallel SVM algorithm.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

“…To analyse the time complexity of the PSVM-MR algorithm, we compared it with L-SVM [12], DC-SVM [10], SVM-SMO-SGD [15], DQLS-SVM, and IRWLS-SVM [13] algorithms. The L-SVM algorithm uses the kernel Fisher discriminant to reduce the distributive deviation of subsets, which leads to good data partition performance.…”

Section: Time Complexitymentioning

confidence: 99%

PSVM-MR: A Parallel Support Vector Machine Algorithm Based on MapReduce

Mao,

Neelakandan

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Alfaro et al [37] introduced a novel method for accelerated training of parallel support vector machines based on ensembles. Song et al [38] proposed an accelerator for the SVM algorithm based on local geometrical information.…”

Section: Related Workmentioning

confidence: 99%

Multi-Angle Fast Neural Tangent Kernel Classifier

Zhai

Liu

2022

Applied Sciences

View full text Add to dashboard Cite

Multi-kernel learning methods are essential kernel learning methods. Still, the base kernel functions in most multi-kernel learning methods only with select kernel functions with shallow structures, which are weak for large-scale uneven data. We propose two types of acceleration models from a multidimensional perspective of the data: the neural tangent kernel (NTK)-based multi-kernel learning method is proposed, where the NTK kernel regressor is shown to be equivalent to an infinitely wide neural network predictor, and the NTK with deep structure is used as the base kernel function to enhance the learning ability of multi-kernel models; and a parallel computing kernel model based on data partitioning techniques. An RBF, POLY-based multi-kernel model is also proposed. All models use historical memory-based PSO (HMPSO) for efficient search of parameters within the model. Since NTK has a multi-layer structure and thus has a significant computational complexity, the use of a Monotone Disjunctive Kernel (MDK) to store and train Boolean features in binary achieves a 15–60% training time compression of NTK models in different datasets while obtaining a 1–25% accuracy improvement.

show abstract

“…A well-known framework of partitioned decentralized learning is the Parameter Server framework [13], [14] described in Section VI-B. Applying the block coordinate descent (BCD) method [67], the Parameter Server framework decomposes a large-scale model-optimization problem into a separable target function, e.g., linear regression [68] and support vector machine (SVM) [69], and solves the problem iteratively in a decentralized manner. The framework of partitioned learning is illustrated in Fig.…”

Section: B Partitioned Learningmentioning

confidence: 99%

Distributed Machine Learning for Wireless Communication Networks: Techniques, Architectures, and Applications

Chen

et al. 2020

Preprint

View full text Add to dashboard Cite

Distributed machine learning (DML) techniques, such as federated learning, partitioned learning, and distributed reinforcement learning, have been increasingly applied to wireless communications. This is due to improved capabilities of terminal devices, explosively growing data volume, congestion in the radio interfaces, and increasing concern of data privacy. The unique features of wireless systems, such as large scale, geographically dispersed deployment, user mobility, and massive amount of data, give rise to new challenges in the design of DML techniques. There is a clear gap in the existing literature in that the DML techniques are yet to be systematically reviewed for their applicability to wireless systems. This survey bridges the gap by providing a contemporary and comprehensive survey of DML techniques with a focus on wireless networks. Specifically, we review the latest applications of DML in power control, spectrum management, user association, and edge cloud computing. The optimality, scalability, convergence rate, computation cost, and communication overhead of DML are analyzed. We also discuss the potential adversarial attacks faced by DML applications, and describe state-of-the-art countermeasures to preserve privacy and security. Last but not least, we point out a number of key issues yet to be addressed, and collate potentially interesting and challenging topics for future research.

show abstract

An accelerator for support vector machines based on the local geometrical information and data partition

Cited by 7 publications

References 31 publications

PSVM-MR: A Parallel Support Vector Machine Algorithm Based on MapReduce

PSVM-MR: A Parallel Support Vector Machine Algorithm Based on MapReduce

Multi-Angle Fast Neural Tangent Kernel Classifier

Distributed Machine Learning for Wireless Communication Networks: Techniques, Architectures, and Applications

Contact Info

Product

Resources

About