Abstract
This work describes a new variant of projective splitting for solving maximal monotone inclusions and complicated convex optimization problems. In the new version, cocoercive operators can be processed with a single forward step per iteration. In the convex optimization context, cocoercivity is equivalent to Lipschitz differentiability. Prior forward-step versions of projective splitting did not fully exploit cocoercivity and required two forward steps per iteration for such operators. Our new single-forward-step method establishes a symmetry between projective splitting algorithms, the classical forward–backward splitting method (FB), and Tseng’s forward-backward-forward method. The new procedure allows for larger stepsizes for cocoercive operators: the stepsize bound is \(2\beta\) for a \(\beta\)-cocoercive operator, the same bound as has been established for FB. We show that FB corresponds to an unattainable boundary case of the parameters in the new procedure. Unlike FB, the new method allows for a backtracking procedure when the cocoercivity constant is unknown. Proving convergence of the algorithm requires some departures from the prior proof framework for projective splitting. We close with some computational tests establishing competitive performance for the method.
Similar content being viewed by others
Notes
If backtracking is used, then all three of these methods can converge under weaker local continuity assumptions.
The breast cancer dataset is available at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE1379. The IBD dataset is available at https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3365.
The C1 dataset is available at http://software.broadinstitute.org/gsea/index.jsp.
Overlapping group norms can also be handled with our method, but using a different problem formulation than (57).
TripAdvisor data is available at https://github.com/yanxht/TripAdvisorData or through our repository at https://github.com/projective-splitting/coco.
References
Alotaibi, A., Combettes, P.L., Shahzad, N.: Solving coupled composite monotone inclusions by successive Fejér approximations of their Kuhn–Tucker set. SIAM J. Optim. 24(4), 2076–2095 (2014)
Baillon, J.B., Haddad, G.: Quelques propriétés des opérateurs angle-bornés \(n\)-cycliquement monotones. Isr. J. Math. 26(2), 137–150 (1977)
Bauschke, H.H., Combettes, P.L.: The Baillon-Haddad theorem revisited. J. Convex Anal. 17(3–4, SI), 781–787 (2010)
Bauschke, H.H., Combettes, P.L.: Convex Analysis and Monotone Operator Theory in Hilbert Spaces, 2nd edn. Springer, Berlin (2017)
Beck, A., Teboulle, M.: Fast gradient-based algorithms for constrained total variation image denoising and deblurring problems. IEEE Trans. Image Process. 18(11), 2419–2434 (2009)
Burczynski, M.E., Peterson, R.L., Twine, N.C., Zuberek, K.A., Brodeur, B.J., Casciotti, L., Maganti, V., Reddy, P.S., Strahs, A., Immermann, F., et al.: Molecular classification of Crohn’s disease and ulcerative colitis patients using transcriptional profiles in peripheral blood mononuclear cells. J. Mol. Diagn. 8(1), 51–61 (2006)
Chambolle, A., Pock, T.: A first-order primal-dual algorithm for convex problems with applications to imaging. J. Math. Imaging Vis. 40(1), 120–145 (2011)
Combettes, P.L.: Systems of structured monotone inclusions: duality, algorithms, and applications. SIAM J. Optim. 23(4), 2420–2447 (2013)
Combettes, P.L., Eckstein, J.: Asynchronous block-iterative primal-dual decomposition methods for monotone inclusions. Math. Program. 168(1–2), 645–672 (2018)
Combettes, P.L., Pesquet, J.C.: Proximal splitting methods in signal processing. In: Fixed-Point Algorithms for Inverse Problems in Science and Engineering, pp. 185–212. Springer, Berlin (2011)
Combettes, P.L., Pesquet, J.C.: Primal-dual splitting algorithm for solving inclusions with mixtures of composite, Lipschitzian, and parallel-sum type monotone operators. Set-Valued Var. Anal. 20(2), 307–330 (2012)
Condat, L.: A primal-dual splitting method for convex optimization involving Lipschitzian, proximable and linear composite terms. J. Optim. Theory Appl. 158(2), 460–479 (2013)
Davis, D., Yin, W.: A three-operator splitting scheme and its optimization applications. Set-Valued Var. Anal. 25(4), 829–858 (2017)
Diamond, S., Boyd, S.: CVXPY: a Python-embedded modeling language for convex optimization. J. Mach. Learn. Res. 17(83), 1–5 (2016)
Eckstein, J.: A simplified form of block-iterative operator splitting and an asynchronous algorithm resembling the multi-block alternating direction method of multipliers. J. Optim. Theory Appl. 173(1), 155–182 (2017)
Eckstein, J., Svaiter, B.F.: A family of projective splitting methods for the sum of two maximal monotone operators. Math. Program. 111(1), 173–199 (2008)
Eckstein, J., Svaiter, B.F.: General projective splitting methods for sums of maximal monotone operators. SIAM J. Control Optim. 48(2), 787–811 (2009)
Gabay, D.: Applications of the method of multipliers to variational inequalities. In: Fortin, M., Glowinski, R. (Eds.) Augmented Lagrangian Methods: Applications to the Solution of Boundary Value Problems, chap. IX, pp. 299–340. North-Holland, Amsterdam (1983)
Johnstone, P.R., Eckstein, J.: Projective splitting with forward steps. Math. Program. (2020). https://doi.org/10.1007/s10107-020-01565-3
Johnstone, P.R., Eckstein, J.: Projective splitting with forward steps only requires continuity. Optim. Lett. 14(1), 229–247 (2020)
Johnstone, P.R., Eckstein, J.: Convergence rates for projective splitting. SIAM J. Optim. 29(3), 1931–1957 (2019)
Johnstone, P.R., Eckstein, J.: Single-forward-step projective splitting: exploiting cocoercivity. arXiv preprint arXiv:1902.09025 (2019)
Korpelevich, G.: Extragradient method for finding saddle points and other problems. Matekon 13(4), 35–49 (1977)
Lions, P.L., Mercier, B.: Splitting algorithms for the sum of two nonlinear operators. SIAM J. Numer. Anal. 16(6), 964–979 (1979)
Ma, X.J., Wang, Z., Ryan, P.D., Isakoff, S.J., Barmettler, A., Fuller, A., Muir, B., Mohapatra, G., Salunga, R., Tuggle, J.T., et al.: A two-gene expression ratio predicts clinical outcome in breast cancer patients treated with tamoxifen. Cancer Cell 5(6), 607–616 (2004)
Machado, M.P.: On the complexity of the projective splitting and Spingarn’s methods for the sum of two maximal monotone operators. J. Optim. Theory Appl. 178(1), 153–190 (2018)
Machado, M.P.: Projective method of multipliers for linearly constrained convex minimization. Comput. Optim. Appl. 73(1), 237–273 (2019)
Malitsky, Y., Pock, T.: A first-order primal-dual algorithm with linesearch. SIAM J. Optim. 28(1), 411–432 (2018)
Malitsky, Y., Tam, M.K.: A forward-backward splitting method for monotone inclusions without cocoercivity. SIAM J. Optim. 30(2), 1451–1472 (2020)
Michelot, C.: A finite algorithm for finding the projection of a point onto the canonical simplex of \(\mathbb{R}^n\). J. Optim. Theory Appl. 50(1), 195–200 (1986)
Pedregosa, F., Gidel, G.: Adaptive three-operator splitting. In: Proceedings of the 35th International Conference on Machine Learning (ICML-18), pp. 4085–4094 (2018)
Pesquet, J.C., Repetti, A.: A class of randomized primal-dual algorithms for distributed optimization. J. Nonlinear Convex Anal. 16(12), 2453–2490 (2015)
Polyak, B.T.: Introduction to Optimization. Optimization Software Inc., Publications Division, New York (1987)
Simon, N., Friedman, J., Hastie, T., Tibshirani, R.: A sparse-group lasso. J. Comput. Graph. Stat. 22(2), 231–245 (2013)
Subramanian, A., Tamayo, P., Mootha, V.K., Mukherjee, S., Ebert, B.L., Gillette, M.A., Paulovich, A., Pomeroy, S.L., Golub, T.R., Lander, E.S., et al.: Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles. Proc. Natl. Acad. Sci. 102(43), 15545–15550 (2005)
Tran-Dinh, Q., Vũ, B.C.: A new splitting method for solving composite monotone inclusions involving parallel-sum operators. Preprint arXiv:1505.07946 (2015)
Tseng, P.: A modified forward–backward splitting method for maximal monotone mappings. SIAM J. Control Optim. 38(2), 431–446 (2000)
Vũ, B.C.: A variable metric extension of the forward–backward–forward algorithm for monotone operators. Numer. Funct. Anal. Optim. 34(9), 1050–1065 (2013)
Wang, H., Lu, Y., Zhai, C.: Latent aspect rating analysis on review text data: a rating regression approach. In: Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 783–792 (2010)
Yan, X., Bien, J.: Rare Feature Selection in High Dimensions. J. Am. Stat. Assoc. (2020). https://doi.org/10.1080/01621459.2020.1796677
Acknowledgements
We thank Xiaohan Yan and Jacob Bien for kindly sharing their data for the TripAdvisor reviews problem in Sect. 6.3. This research was supported by the National Science Foundation Grant CCF-1617617.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Johnstone, P.R., Eckstein, J. Single-forward-step projective splitting: exploiting cocoercivity. Comput Optim Appl 78, 125–166 (2021). https://doi.org/10.1007/s10589-020-00238-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10589-020-00238-3