Systems and Means of Informatics
2021, Volume 31, Issue 1, pp 4-16
CONCORDANT MODELS FOR LATENT SPACE PROJECTIONS IN FORECASTING
- F. Yu. Yaushev
- R. V. Isachenko
- V. V. Strijov
Abstract
The paper examines the problem of predicting a complex structured target variable. Complexity refers to the presence of dependencies, whether linear or nonlinear. The source data are assumed to be heterogeneous. This means that the spaces of the independent and target variables are of different nature. It is proposed to build a predictive model that takes into account the dependence in the input space of the independent variable as well as in the space of the target variable. It is proposed to make a model agreement procedure in a lowdimensional latent space. The projection to the latent space method is used as the basic algorithm. The paper compares the linear and proposed nonlinear models.
The comparison is performed on heterogeneous data in high-dimensional spaces.
[+] References (17)
- Rosipal, R., N. Kramer, and A. Graves. 2005. Overview and recent advances in partial least squares. Subspace, Latent Structure and Feature Selection: Statistical and Optimization Perspectives Workshop. Eds. C. Saunders, M. Grobelnik, S. Gunn, and J. Shawe-Taylor. Lecture notes in computer science ser. Springer. 3940:34-51.
- Rosipal, R. 2011. Nonlinear partial least squares: An overview. Chemoinformatics and advanced machine learning perspectives: Complex computational methods and collaborative techniques. Eds. H. Lodhi and Y. Yamanishi. IGI Global. 169-189.
- Worsley, K. J. 1997. An overview and some new developments in the statistical analysis of pet and fmri data. Hum. Brain Mapp. 5:254-258.
- Hulland, J. S. 1999. Use of partial least squares (pls) in strategic management research: A review of four recent studies. Strateg. Manage. J. 20:195-204.
- Shalamu Abudu, P. E., and T. C. Pagano. 2010. Application of partial least-squares regression in seasonalstreamflow forecasting. J. Hydrol. Eng. 15:612-623.
- Nguyen, D. V., and D. M. Rocke. 2012. Tumor classification by partial least squares using microarray gene expression data. Bioinformatics 18:39-50.
- Szedmak, S. R., D. R. Hardoon, and J. R. Shawe-Taylor. 2004. Canonical correlation analysis: An overview with application to learning methods. Neural Comput. 16:26392664.
- Schechner, Y. Y., E. Kidron, and M. Elad. 2005. Pixels that sound. Computer Vision and Pattern Recognition Conference. IEEE Computer Society. 1:88-95.
- Sun, S., L. Ji, and J. Ye. 2008. A least squares formulation for canonical correlation analysis. 25th Conference (International) on Machine Learning Proceedings. ACM. 1024-1031.
- Qin, S. J., and T. J. McAvoy. 1992. Nonlinear pls modeling using neural networks. Comput. Chem. Eng. 16:379-391.
- Hiden, M., B. McKay, and G. Montague. 1998. Non-linear partial least squares using genetic programming. Genetic programming. San Francisco, CA: Morgan Kaufmann. 128-133.
- Chen, D. Z., X. F. Yan, and S. X. Hu. 2003. Chaos-genetic algorithms for optimizing the operating conditions based on rbf-pls model. Comput. Chem. Eng. 27:1393-1404.
- Lai, P. L., and C. Fyfe. 2000. Kernel and nonlinear canonical correlation analysis. Int. J. Neural Systems 10:365-377.
- Galen, A., R. Arora, J. Bilmes, and K. Livensen. 2013. Deep canonical correlation analysis. PMLR 28(3):1247-1255.
- Yan, F., and K. Mikolajczyk. 2015. Deep correlation for matching images and text. Proc. CVPR IEEE 4:3441-3450.
- LeCun, Y., C. Cortes, and C. Burges. 1998. The MNIST dataset of handwritten digits. Available at: http://yann. lecun.com/exdb/mnist/index.html (accessed February 24, 2021).
- Yaushev, F.Yu, and R.V. Isachenko. 2020. Modeli soglasovaniya skrytogo pros- transtva v zadache prognozirovaniya [Concordant models for latent space projections in the complex structured prediction tasks]. Available at: https://github.com/Fyaushev/ 2020-Project-72 (accessed February 24, 2021).
[+] About this article
Title
CONCORDANT MODELS FOR LATENT SPACE PROJECTIONS IN FORECASTING
Journal
Systems and Means of Informatics
Volume 31, Issue 1, pp 4-16
Cover Date
2021-04-20
DOI
10.14357/08696527210101
Print ISSN
0869-6527
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
prediction; partial least squares; model concordance; nonlinear projection to latent space
Authors
F. Yu. Yaushev  , R. V. Isachenko , and V. V. Strijov , 
Author Affiliations
Moscow Institute of Physics and Technology, 9 Institutskiy Per., Dolgoprudny, Moscow Region 141700, Russian Federation
A. A. Dorodnicyn Computing Center, Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences, 40 Vavilov Str., Moscow 119333, Russian Federation
|