Abstract
The paper examines four weak relaxed greedy algorithms for finding approximate sparse solutions of convex optimization problems in a Banach space. First, we present a review of primal results on the convergence rate of the algorithms based on the geometric properties of the objective function. Then, using the ideas of [16], we define the duality gap and prove that the duality gap is a certificate for the current approximation to the optimal solution. Finally, we find estimates of the dependence of the duality gap values on the number of iterations for weak greedy algorithms.
This work was supported by the Russian Fund for Basic Research, projects 16-01-00507, 18-01-00408.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Barron, A.R., Cohen, A., Dahmen, W., DeVore, R.A.: Approximation and learning by greedy algorithms. Ann. Stat. 36(1), 64–94 (2008)
Blumensath, T., Davies, M.E.: Gradient pursuits. IEEE Trans. Signal Process. 56, 2370–2382 (2008)
Blumensath, T., Davies, M.: Stagewise weak gradient pursuits. IEEE Trans. Signal Process. 57, 4333–4346 (2009)
Bubeck, S.: Convex optimization: algorithms and complexity. Found. Trends Mach. Learn. 8(3–4), 231–358 (2015)
Clarkson, K.L.: Coresets, sparse greedy approximation, and the Frank-Wolfe algorithm. ACM Trans. Algorithms 6(4), 1–30 (2010)
Davis, G., Mallat, S., Avellaneda, M.: Adaptive greedy approximation. Constr. Approx. 13, 57–98 (1997)
Demyanov, V., Rubinov, A.: Approximate Methods in Optimization Problems. American Elsevier Publishing Co., New York (1970)
Dereventsov, A.V.: On the approximate weak Chebyshev greedy algorithm in uniformly smooth banach spaces. J. Math. Anal. Appl. 436(1), 288–304 (2016)
DeVore, R.A., Temlyakov, V.N.: Some remarks on greedy algorithms. Adv. Comput. Math. 5, 173–187 (1996)
DeVore, R.A., Temlyakov, V.N.: Convex optimization on Banach spaces. Found. Comput. Math. 16(2), 369–394 (2016)
Frank, M., Wolfe, P.: An algorithm for quadratic programming. Naval Res. Logis. Quart. 3, 95–110 (1956)
Freund, R.M., Grigas, P.: New analysis and results for the Frank-Wolfe method. Math. Program. 155(1), 199–230 (2016)
Friedman, J.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29(5), 1189–1232 (2001)
Georgiev, P.G., Sánchez-González, L., Pardalos, P.M.: Construction of pairs of reproducing kernel Banach spaces. In: Demyanov, V., Pardalos, P., Batsyn, M. (eds.) Constructive Nonsmooth Analysis and Related Topics. SOIA, vol. 87, pp. 39–57. Springer, New York (2014). https://doi.org/10.1007/978-1-4614-8615-2_4
Huber, P.J.: Projection pursuit. Ann. Statist. 13, 435–525 (1985)
Jaggi, M.: Revisiting Frank-Wolfe: projection-free sparse convex optimization. In: Proceedings of the 30th International Conference on Machine Learning (ICML-13), pp. 427–435 (2013)
Jones, L.: On a conjecture of Huber concerning the convergence of projection pursuit regression. Ann. Statist. 15, 880–882 (1987)
Konyagin, S.V., Temlyakov, V.N.: A remark on greedy approximation in Banach spaces. East J. Approx. 5(3), 365–379 (1999)
Levitin, E.S., Polyak, B.T.: Constrained minimization methods. USSR Comp. Math. M. Phys. 6(5), 1–50 (1966)
Nemirovski, A.: Optimization II: Numerical methods for nonlinear continuous optimization. Lecture Notes, Israel Institute of Technology (1999)
Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course. Kluwer Academic Publishers, Boston (2004)
Nguyen, H., Petrova, G.: Greedy strategies for convex optimization. Calcolo 41(2), 1–18 (2016)
Polyak, B.T.: Introduction to Optimization. Optimization Software Inc., New York (1987)
Temlyakov, V.N.: Greedy approximation in convex optimization. Constr. Approx. 41(2), 269–296 (2015)
Temlyakov, V.N.: Dictionary descent in optimization. Anal. Mathematica 42(1), 69–89 (2016)
Zhang, H., Zhang, J.: Learning with reproducing Kernel Banach spaces. In: Dang, P., Ku, M., Qian, T., Rodino, L.G. (eds.) New Trends in Analysis and Interdisciplinary Applications. TM, pp. 417–423. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-48812-7_53
Zhang, Z., Shwartz, S., Wagner, L., Miller, W.: A greedy algorithm for aligning DNA sequences. J. Comput. Biol. 7(1–2), 203–214 (2000)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Sidorov, S.P., Mironov, S.V., Pleshakov, M.G. (2018). Dual Convergence Estimates for a Family of Greedy Algorithms in Banach Spaces. In: Nicosia, G., Pardalos, P., Giuffrida, G., Umeton, R. (eds) Machine Learning, Optimization, and Big Data. MOD 2017. Lecture Notes in Computer Science(), vol 10710. Springer, Cham. https://doi.org/10.1007/978-3-319-72926-8_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-72926-8_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-72925-1
Online ISBN: 978-3-319-72926-8
eBook Packages: Computer ScienceComputer Science (R0)