Abstract
This paper presents two new approximate versions of the alternating direction method of multipliers (ADMM) derived by modifying of the original “Lagrangian splitting” convergence analysis of Fortin and Glowinski. They require neither strong convexity of the objective function nor any restrictions on the coupling matrix. The first method uses an absolutely summable error criterion and resembles methods that may readily be derived from earlier work on the relationship between the ADMM and the proximal point method, but without any need for restrictive assumptions to make it practically implementable. It permits both subproblems to be solved inexactly. The second method uses a relative error criterion and the same kind of auxiliary iterate sequence that has recently been proposed to enable relative-error approximate implementation of non-decomposition augmented Lagrangian algorithms. It also allows both subproblems to be solved inexactly, although ruling out “jamming” behavior requires a somewhat complicated implementation. The convergence analyses of the two methods share extensive underlying elements.
Similar content being viewed by others
Notes
The analysis in [21] has this formal assumption, but it is not clear whether it is absolutely necessary. For ISTA and FISTA it is an definite requirement, although in the backtracking variant of FISTA we need not know the exact value of the Lipschitz constant.
These methods do have box-constrained variants, which correspond to the particular case that g is the indicator function of a “box”. However, such algorithms tend to have rather intricate “hybrid” structure and are dependent on the facial structure of the box.
References
Alves, M.M., Svaiter, B.F.: A note on Fejér-monotone sequences in product spaces and its applications to the dual convergence of augmented Lagrangian methods. Math. Program. 155(1–2), 613–616 (2016)
Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2(1), 183–202 (2009)
Birgin, E.G., Martínez, J.M.: Practical Augmented Lagrangian Methods for Constrained Optimization. SIAM, Philadelphia (2014)
Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.: Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn. 3(1), 1–122 (2011)
Chambolle, A., DeVore, R.A., Lee, N.Y., Lucier, B.J.: Nonlinear wavelet image processing: variational problems, compression, and noise removal through wavelet shrinkage. IEEE Trans. Image Process. 7(3), 319–335 (1998)
Dettling, M., Bühlmann, P.: Finding predictive gene groups from microarray data. J. Multivar. Anal. 90(1), 106–131 (2004)
Duarte, M.F., Davenport, M.A., Takbar, D., Laska, J.N., Sun, T., Kelly, K.F., Baraniuk, R.G.: Single-pixel imaging via compressive sampling: building simpler, smaller, and less-expensive digital cameras. IEEE Sig. Process. Mag. 25(2), 83–91 (2008)
Eckstein, J.: Splitting methods for monotone operators with applications to parallel optimization. Ph.D. thesis, Massachusetts Institute of Technology (1989)
Eckstein, J.: Some saddle-function splitting methods for convex programming. Optim. Methods Softw. 4(1), 75–83 (1994)
Eckstein, J.: A practical general approximation criterion for methods of multipliers based on Bregman distances. Math. Program. 96(1), 61–86 (2003)
Eckstein, J., Bertsekas, D.P.: On the Douglas–Rachford splitting method and the proximal point algorithm for maximal monotone operators. Math. Program. 55(3), 293–318 (1992)
Eckstein, J., Silva, P.J.S.: A practical relative error criterion for augmented Lagrangians. Math. Program. 141(1–2), 319–348 (2013)
Eckstein, J., Yao, W.: Approximate versions of the alternating direction method of multipliers. Tech. Rep. 2016-01-5276, Optimization Online (2016)
Fan, R.E., Chen, P.H., Lin, C.J.: Working set selection using second order information for training support vector machines. J. Mach. Learn. Res. 6, 1889–1918 (2005)
Fortin, M., Glowinski, R.: On decomposition-coordination methods using an augmented Lagrangian. In: Fortin, M., Glowinski, R. (eds.) Augmented Lagrangian Methods: Applications to the Numerical Solution of Boundary-Value Problems, Studies in Mathematics and its Applications, vol. 15. North-Holland, Amsterdam (1983)
Franklin, J.: The elements of statistical learning: data mining, inference and prediction. Math. Intell. 27(2), 83–85 (2005)
Gabay, D.: Applications of the method of multipliers to variational inequalities. In: Fortin, M., Glowinski, R. (eds.) Augmented Lagrangian Methods: Applications to the Numerical Solution of Boundary-Value Problems, Studies in Mathematics and its Applications, vol. 15, pp. 299–331. North-Holland, Amsterdam (1983)
Guyon, I., Gunn, S., Ben-Hur, A., Dror, G.: Result analysis of the NIPS 2003 feature selection challenge. In: Saul, L., Weiss, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems 17, pp. 545–552. MIT Press, Cambridge (2005)
He, B.: Inexact implicit methods for monotone general variational inequalities. Math. Program. 86(1), 199–217 (1999)
He, B., Liao, L.Z., Han, D., Yang, H.: A new inexact alternating directions method for monotone variational inequalities. Math. Program. 92(1), 103–118 (2002)
Huang, Y., Liu, H.: A Barzilai-Borwein type method for minimizing composite functions. Numer. Algorithms 69(4), 819–838 (2015)
Kogan, S., Levin, D., Routledge, B.R., Sagi, J.S., Smith, N.A.: Predicting risk from financial reports with regression. In: Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics. NAACL ’09, pp. 272–280. Association for Computational Linguistics, Stroudsburg, PA, USA (2009)
Lichman, M.: UCI machine learning repository (2013). URL http://archive.ics.uci.edu/ml
Liu, D.C., Nocedal, J.: On the limited memory BFGS method for large scale optimization. Math. Program. 45(3), 503–528 (1989)
Ng, A.Y.: Feature selection, \(L_1\) vs. \(L_2\) regularization, and rotational invariance. In: Proceedings, Twenty-First International Conference on Machine Learning, ICML 2004, pp. 615–622 (2004)
Nocedal, J., Wright, S.J.: Numerical Optimization, 2nd edn. Springer, New York (2006)
Polyak, B.T.: Introduction to Optimization. Optimization Software Inc, New York (1987)
Rockafellar, R.T.: Local boundedness of nonlinear, monotone operators. Michigan Math. J. 16, 397–407 (1969)
Rockafellar, R.T.: Convex Analysis. Princeton University Press, Princeton (1970)
Rockafellar, R.T.: Conjugate Duality and Optimization. SIAM, Philadephia (1974)
Solodov, M.V., Svaiter, B.F.: A hybrid projection-proximal point algorithm. J. Convex Anal. 6(1), 59–70 (1999)
Solodov, M.V., Svaiter, B.F.: An inexact hybrid generalized proximal point algorithm and some new results on the theory of Bregman functions. Math. Oper. Res. 25(2), 214–230 (2000)
Tibshirani, R.: Regression shrinkage and selection via the lasso. J. R. Stat. Soc. Ser. B 58(1), 267–288 (1996)
Xie, J., Liao, A., Yang, X.: An inexact alternating direction method of multipliers with relative error criteria. Optim. Lett. 11(3), 583–596 (2017)
Yuan, X.M.: The improvement with relative errors of He et al’.s inexact alternating direction method for monotone variational inequalities. Math. Comput. Model. 42(11–12), 1225–1236 (2005)
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was funded in part by the National Science Foundation under Grant CCF-1115638. The authors would also like to thank Heinz Bauschke for suggesting the Proof of Lemma 1.
Rights and permissions
About this article
Cite this article
Eckstein, J., Yao, W. Approximate ADMM algorithms derived from Lagrangian splitting. Comput Optim Appl 68, 363–405 (2017). https://doi.org/10.1007/s10589-017-9911-z
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10589-017-9911-z