Abstract
The paper examines a class of algorithms called Weak Biorthogonal Greedy Algorithms (WBGA) designed for the task of finding the approximate solution to a convex cardinality-constrained optimization problem in a Banach space using linear combinations of some set of “simple” elements of this space (a dictionary), i.e. the problem of finding the infimum of a given convex function over all linear combinations of the dictionary elements with the given cardinality. An important issue when one computationally solves optimization problems is to obtain an estimate of the proximity to an optimal solution, that can be used to effectively check that the approximate solution is with a given accuracy. A similar idea that has already been applied to solving some optimization problems, in which such an estimate of the proximity (certificate) to the optimal solution is called the “duality gap”. We introduce the notion of the duality gap for greedy optimization in Banach Spaces and obtain dual convergence estimates for sparse-constrained optimization by means of algorithms from the WBGA class.
This work was supported by the Ministry of Science and Higher Education of the Russian Federation in the framework of the basic part of the scientific research state task, project FSRR-2020-0006.
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). https://doi.org/10.1214/009053607000000631
Chena, Z., Huang, C., Lin, S.: A new sparse representation framework for compressed sensing mri. Knowl. Based Syst. 188, 104969 (2020). https://doi.org/10.1016/j.knosys.2019.104969
Clarkson, K.L.: Coresets, sparse greedy approximation, and the frank-wolfe algorithm. ACM Trans. Algorithms 6(4), 1–30 (2010). https://doi.org/10.1145/1824777.1824783
Davis, G., Mallat, S., Avellaneda, M.: Adaptive greedy approximation. Constr. Approx. 13(1), 57–98 (1997). https://doi.org/10.1007/bf02678430
Dereventsov, A., Temlyakov, V.: A unified way of analyzing some greedy algorithms. J. Funct. Anal. 277(12), 108286 (2019). https://doi.org/10.1016/j.jfa.2019.108286, http://www.sciencedirect.com/science/article/pii/S0022123619302496
DeVore, R.A., Temlyakov, V.N.: Some remarks on greedy algorithms. Adv. Comput. Math. 5, 173–187 (1996). https://doi.org/10.1007/bf02124742
DeVore, R.A., Temlyakov, V.N.: Convex optimization on banach spaces. Found. Comput. Math. 16(2), 369–394 (2016)
Donoho, D.L.: Compressed sensing. IEEE Trans. Inf. Theory 52(4), 1289–1306 (2006). https://doi.org/10.1109/TIT.2006.871582
Fan, J., Lv, J., Qi, L.: Sparse high-dimensional models in economics. Ann. Rev. Econ. 3(1), 291–317 (2011). https://doi.org/10.1146/annurev-economics-061109-080451
Frank, M., Wolfe, P.: An algorithm for quadratic programming. Naval Res. Logis. Q. 3(1–2), 95–110 (1956). https://doi.org/10.1002/nav.3800030109
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)
Huber, P.J.: Projection pursuit. Ann. Stat. 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-2013), pp. 427–435 (2013)
Jones, L.: On a conjecture of Huber concerning the convergence of projection pursuit regression. Ann. Stat. 15(2), 880–882 (1987). https://doi.org/10.1214/aos/1176350382
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 Comput. Math. Math. Phys. 6(5), 1–50 (1966)
Mironov, S.V., Sidorov, S.P.: Duality gap estimates for weak Chebyshev greedy algorithms in Banach spaces. Comput. Math. Math. Phys. 59(6), 904–914 (2019). https://doi.org/10.1134/S0965542519060113
Nemirovski, A., Onn, S., Rothblum, U.G.: Accuracy certificates for computational problems with convex structure. Math. Oper. Res. 35(1), 52–78 (2010). https://doi.org/10.1287/moor.1090.0427
Nesterov, Y.: Complexity bounds for primal-dual methods minimizing the model of objective function. Math. Program. 171(1-2), 311–330 (2017). https://doi.org/10.1007/s10107-017-1188-6
Nguyen, H., Petrova, G.: Greedy strategies for convex optimization. Calcolo 54(1), 207–224 (2016). https://doi.org/10.1007/s10092-016-0183-2
Sidorov, S.P., Mironov, S.V., Pleshakov, M.G.: Dual convergence estimates for a family of greedy algorithms in Banach spaces. In: Nicosia, G., Pardalos, P., Giuffrida, G., Umeton, R. (eds.) MOD 2017. LNCS, vol. 10710, pp. 109–120. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-72926-8_10
Sidorov, S.P., Faizliev, A.R., Khomchenko, A.A.: Algorithms for \(l_1\)-norm minimisation of index tracking error and their performance. Int. J. Math. Oper. Res. 11(4), 497–519 (2017). https://ideas.repec.org/a/ids/ijmore/v11y2017i4p497-519.html
Sidorov, S.P., Mironov, S.V.: Duality gap analysis of weak relaxed greedy algorithms. In: Battiti, R., Kvasov, D.E., Sergeyev, Y.D. (eds.) LION 2017. LNCS, vol. 10556, pp. 251–262. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-69404-7_18
Temlyakov, V.N.: Greedy approximation in convex optimization. Constr. Approx. 41(2), 269–296 (2015). https://doi.org/10.1007/s00365-014-9272-0
Temlyakov, V.N.: Dictionary descent in optimization. Anal. Mathematica 42(1), 69–89 (2016). https://doi.org/10.1007/s10476-016-0106-0
Zhang, Z., Shwartz, S., Wagner, L., Miller, W.: A greedy algorithm for aligning DNA sequences. J. Comput. Biol. 7(1–2), 203–214 (2000). https://doi.org/10.1089/10665270050081478
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Sidorov, S., Spiridinov, K. (2021). Duality Gap Estimates for a Class of Greedy Optimization Algorithms in Banach Spaces. In: Pardalos, P., Khachay, M., Kazakov, A. (eds) Mathematical Optimization Theory and Operations Research. MOTOR 2021. Lecture Notes in Computer Science(), vol 12755. Springer, Cham. https://doi.org/10.1007/978-3-030-77876-7_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-77876-7_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-77875-0
Online ISBN: 978-3-030-77876-7
eBook Packages: Computer ScienceComputer Science (R0)