Abstract
Kernel independent component analysis (KICA) penalizes the correlations among components in a reproducing kernel Hilbert space (RKHS) and performs well in many practical tasks such as speech separation due to its robustness on varying source distributions. Recently, Nyström-KICA (NKICA) incorporates a low-rank approximation and low-complexity sampling method to reduce the computational complexity of KICA. In this paper, we show that the computational complexity of NKICA can be further decreased by implementing the algorithm on the many integrated core (MIC) architecture to meet the requirement of large data processing. Particularly, we parallelize the critical segments with the OpenMP technology and perform the intensive matrix manipulations on a MIC coprocessor. This MIC-based approach has been evaluated on both simulated dataset and the TIMIT dataset. The experimental results confirm the efficiency of our implementation of NKICA on the MIC architecture, and show that it achieves a consistent speedup rate of around 10 on average, and of 12.3 at best, comparing with that performed on single CPU.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hyvärinen, A., Oja, E.: A fast fixed-point algorithm for independent component analysis. Neural Comput. 9(7), 1483–1492 (1997)
Du, K.L., Swamy, M.: Independent Component Analysis: Neural Networks and Statistical Learning, pp. 419–450. Springer, London (2014)
Hyvärinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. Wiley, New York (2004)
Bach, F.R., Jordan, M.I.: Kernel independent component analysis. J. Mach. Learn. Res. 3, 1–48 (2003)
Shen, H., Jegelka, S., Gretton, A.: Fast kernel-based independent component analysis. IEEE Trans. Sign. Process. 57(9), 3498–3511 (2009)
Williams, C., Seeger, M.: The effect of the input density distribution on kernel-based classifiers. In: Proceedings of the 17th International Conference on Machine Learning, no. EPFL-CONF-161323, pp. 1159–1166 (2000)
Kumar, S., Mohri, M., Talwalkar, A.: Sampling techniques for the Nyström method. In: International Conference on Artificial Intelligence and Statistics, pp. 304–311 (2009)
Wang, H., Xu, W., Guan, N., Yang, C.: Fast kernel independent component analysis with Nyström method. In: International Conference on Signal Processing (2016)
Duran, A., Klemm, M.: The intel many integrated core architecture. In: 2012 International Conference on High Performance Computing and Simulation (HPCS), pp. 365–366. IEEE (2012)
Jeffers, J., Reinders, J.: Intel Xeon Phi coprocessor high-performance programming. Newnes (2013)
Chrysos, G.: Intel xeon phi coprocessor-the architecture. Intel Whitepaper (2014)
Tarditi, D., Puri, S., Oglesby, J.: Accelerator: using data parallelism to program gpus for general-purpose uses. In: ACM SIGARCH Computer Architecture News, vol. 34, no. 5, pp. 325–335. ACM (2006)
Lee, S., Min, S.J., Eigenmann, R.: OpenMP to GPGPU: a compiler framework for automatic translation and optimization. ACM Sigplan Notices 44(4), 101–110 (2009)
Garofolo, J.S., Lamel, L.F., Fisher, W.M., Fiscus, J.G., Pallett, D.S.: DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. nist speech disc 1–1.1, NASA STI/Recon Technical report N, vol. 93 (1993)
Guan, N., Lan, L., Tao, D., Luo, Z., Yang, X.: Transductive nonnegative matrix factorization for semi-supervised high-performance speech separation. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2534–2538. IEEE (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Shan, L., Wang, H., Xu, W., Yang, C., Zhang, M. (2016). Accelerating Nyström Kernel Independent Component Analysis with Many Integrated Core Architecture. In: Xu, W., Xiao, L., Li, J., Zhang, C., Zhu, Z. (eds) Computer Engineering and Technology. NCCET 2016. Communications in Computer and Information Science, vol 666. Springer, Singapore. https://doi.org/10.1007/978-981-10-3159-5_16
Download citation
DOI: https://doi.org/10.1007/978-981-10-3159-5_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3158-8
Online ISBN: 978-981-10-3159-5
eBook Packages: Computer ScienceComputer Science (R0)