Advertisement

Learning Augmented Methods

Chapter
  • 218 Downloads

Abstract

In this chapter, we introduce some cutting-edge learning augmented techniques to enhance the performance of structured signal processing. We start with compressed sensing under a generative prior, which can better capture the underlying signal structure than the traditional sparse prior. We then present learning augmented techniques for the joint design of measurement matrix and sparse support recovery for the sparse linear model (e.g., compressed sensing). Furthermore, several deep-learning-based AMP methods for the sparse linear model are introduced, including learned AMP, learned Vector-AMP, and learned ISTA for group row sparsity.

References

  1. 1.
    Asim, M., Shamshad, F., Ahmed, A.: Blind image deconvolution using deep generative priors (2018). Preprint. arXiv: 1802.04073Google Scholar
  2. 2.
    Bonnefoy, A., Emiya, V., Ralaivola, L., Gribonval, R.: Dynamic screening: accelerating first-order algorithms for the lasso and group-lasso. IEEE Trans. Signal Process. 63(19), 5121–5132 (2015)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Bora, A., Jalal, A., Price, E., Dimakis, A.G.: Compressed sensing using generative models. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 537–546 (2017). JMLR. orgGoogle Scholar
  4. 4.
    Borgerding, M., Schniter, P., Rangan, S.: AMP-inspired deep networks for sparse linear inverse problems. IEEE Trans. Signal Process. 65(16), 4293–4308 (2017)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Chen, X., Liu, J., Wang, Z., Yin, W.: Theoretical linear convergence of unfolded ISTA and its practical weights and thresholds. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 9061–9071 (2018)Google Scholar
  6. 6.
    Duarte-Carvajalino, J.M., Sapiro, G.: Learning to sense sparse signals: simultaneous sensing matrix and sparsifying dictionary optimization. IEEE Trans. Image Process. 18(7), 1395–1408 (2009)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Elad, M.: Optimized projections for compressed sensing. IEEE Trans. Signal Process. 55(12), 5695–5702 (2007)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Proceedings of the Neural Information Processing Systems (NeurIPS), pp. 2672–2680 (2014)Google Scholar
  9. 9.
    Gregor, K., LeCun, Y.: Learning fast approximations of sparse coding. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 399–406. Omnipress, Madison (2010)Google Scholar
  10. 10.
    Hao, J., Zhang, B., Jiao, Z., Mao, S.: Adaptive compressive sensing based sample scheduling mechanism for wireless sensor networks. Pervasive Mob. Comput. 22, 113–125 (2015)CrossRefGoogle Scholar
  11. 11.
    Kingma, D.P., Ba, J.: ADAM: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (ICLR) (2015)Google Scholar
  12. 12.
    Kingma, D.P., Welling, M.: Auto-encoding variational Bayes (2013). Preprint. arXiv: 1312.6114Google Scholar
  13. 13.
    Li, S., Zhang, W., Cui, Y., Cheng, H.V., Yu, W.: Joint design of measurement matrix and sparse support recovery method via deep auto-encoder. Preprint. arXiv: 1910.04330 (2019)Google Scholar
  14. 14.
    Mangia, M., Rovatti, R., Setti, G.: Rakeness in the design of analog-to-information conversion of sparse and localized signals. IEEE Trans. Circuits Syst. I, Reg. Papers 59(5), 1001–1014 (2012)Google Scholar
  15. 15.
    Mangia, M., Pareschi, F., Rovatti, R., Setti, G.: Adaptive matrix design for boosting compressed sensing. IEEE Trans. Circuits Syst. I, Reg. Papers 65(3), 1016–1027 (2017)Google Scholar
  16. 16.
    Mousavi, A., Baraniuk, R.G.: Learning to invert: signal recovery via deep convolutional networks. In: Proceedings of the IEEE International Conference on Acoustics Speech Signal Processing (ICASSP), pp. 2272–2276. IEEE, Piscataway (2017)Google Scholar
  17. 17.
    Mousavi, A., Dasarathy, G., Baraniuk, R.G.: DeepCodec: adaptive sensing and recovery via deep convolutional neural networks. In: Annual Allerton Conference on Communication, Control, and Computing (Allerton), pp. 744–744. IEEE, Piscataway (2017)Google Scholar
  18. 18.
    Mousavi, A., Dasarathy, G., Baraniuk, R.G.: A data-driven and distributed approach to sparse signal representation and recovery. In: Proceedings of the International Conference on Learning Representations (ICLR) (2019)Google Scholar
  19. 19.
    Rangan, S., Schniter, P., Fletcher, A.K.: Vector approximate message passing. IEEE Trans. Inf. Theory 65, 6664–6684 (2019)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Taha, A., Alrabeiah, M., Alkhateeb, A.: Enabling large intelligent surfaces with compressive sensing and deep learning (2019). Preprint. arXiv: 1904.10136Google Scholar
  21. 21.
    Tibshirani, R.: Regression shrinkage and selection via the lasso. J. R. Stat. Soc. 58(1), 267–288 (1996)MathSciNetzbMATHGoogle Scholar
  22. 22.
    Wu, S., Dimakis, A., Sanghavi, S., Yu, F., Holtmann-Rice, D., Storcheus, D., Rostamizadeh, A., Kumar, S.: Learning a compressed sensing measurement matrix via gradient unrolling. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 6828–6839 (2019)Google Scholar
  23. 23.
    Wu, Y., Rosca, M., Lillicrap, T.: Deep compressed sensing. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 6850–6860 (2019)Google Scholar
  24. 24.
    Xu, J., Pi, Y., Cao, Z.: Optimized projection matrix for compressive sensing. EURASIP J. Adv. Signal Process. 2010(1), 560349 (2010)CrossRefGoogle Scholar
  25. 25.
    Yao, S., Zhao, Y., Zhang, A., Su, L., Abdelzaher, T.: DeepIoT: compressing deep neural network structures for sensing systems with a compressor-critic framework. In: Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems, p. 4. ACM, New York (2017)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.School of Information Science and TechnologyShanghai Tech UniversityShanghaiChina
  2. 2.School of Information Science and TechnologyShanghaiTech UniversityShanghaiChina
  3. 3.Department of Electronic & Information EngineeringHong Kong Polytechnic UniversityKowloonHong Kong

Personalised recommendations