Abstract
We present a new modification of gradient descent algorithm based on surrogate optimization with projection into low-dimensional space. It consequently builds an approximation of the target function in low-dimensional space and takes the approximation optimum point mapped back to original parameter space as the next parameter estimate. An additional projection step is used to fight the curse of dimensionality. Major advantage of the proposed modification is that it does not change gradient descent iterations, thus it may be used with almost any zero- or first-order iterative method. We give a theoretical motivation for the proposed algorithm and experimentally illustrate its properties on modelled data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Box, G.E., Draper, N.R., et al.: Empirical Model-Building and Response Surfaces. John Wiley & Sons, New York (1987)
Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press, New York (2004)
Ford, J., Moghrabi, I.: Multi-step quasi-Newton methods for optimization. J. Comput. Appl. Math. 50(1–3), 305–323 (1994)
Forrester, A., Keane, A.: Recent advances in surrogate-based optimization. Prog. Aerosp. Sci. 45(1), 50–79 (2009)
Granichin, O., Volkovich, V., Toledano-Kitai, D.: Randomized Algorithms in Automatic Control and Data Mining. Springer, Heidelberg (2015)
Granichin, O.N.: Stochastic approximation search algorithms with randomization at the input. Autom. Remote Control 76(5), 762–775 (2015)
Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course. Springer, New York (2004)
Polyak, B.T.: Introduction to Optimization. Translations Series in Mathematics and Engineering. Optimization Software (1987)
Acknowledgments
This work was supported by Russian Science Foundation (project 16-19-00057).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
AÂ Proofs
AÂ Proofs
Proof
(of Proposition 1)
Since \((\mathbf {I}-\mathbf {P}^\top \mathbf {P})\) is not invertible, the above equation has an infinite number of solutions. Hence, we are free to choose any one of them, e.g. \(\mathbf {x}=\frac{1}{K}\sum _1^K \mathbf {x}_t\).
Proof
(of Proposition 2)
Substituting \(\mathbf {v}\) back and taking derivative with respect to \(\mathbf {z}\), we obtain:
Proof
(of Proposition 3) From Propositions 1 and 2: \(\widehat{\mathbf {x}} = \left( \mathbf {I} - \mathbf {P}^\top \mathbf {P}\right) \overline{\mathbf {x}} - \frac{1}{2} \mathbf {P}^\top \mathbf {P} \mathbf {A}^{-1}\mathbf {b} \). Hence
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Senov, A. (2017). Accelerating Gradient Descent with Projective Response Surface Methodology. In: Battiti, R., Kvasov, D., Sergeyev, Y. (eds) Learning and Intelligent Optimization. LION 2017. Lecture Notes in Computer Science(), vol 10556. Springer, Cham. https://doi.org/10.1007/978-3-319-69404-7_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-69404-7_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-69403-0
Online ISBN: 978-3-319-69404-7
eBook Packages: Computer ScienceComputer Science (R0)