Abstract
We extend the Malitsky-Tam forward-reflected-backward (FRB) splitting method for inclusion problems of monotone operators to nonconvex minimization problems. By assuming the generalized concave Kurdyka-Łojasiewicz (KL) property of a quadratic regularization of the objective, we show that the FRB method converges globally to a stationary point of the objective and enjoys the finite length property. Convergence rates are also given. The sharpness of our approach is guaranteed by virtue of the exact modulus associated with the generalized concave KL property. Numerical experiments suggest that FRB is competitive compared to the Douglas-Rachford method and the Boţ-Csetnek inertial Tseng’s method.
Similar content being viewed by others
Data availability
The data that support the findings of Table 1 are available from the corresponding author upon request.
Notes
In the remainder, we shall omit adjectives “pointwise" and “setwise" whenever there is no ambiguity.
We also performed simulations with much larger problem size (\(n=4000,5000,6000\)), in which case FRB, DR, and iTseng tend to stuck at stationary points while DRh can still hit global minimizers. We believe that this is due to its heuristics; see also [6, Section 5].
References
Bauschke, H.H., Combettes, P.L.: Convex Analysis and Monotone Operator Theory in Hilbert Spaces. Springer, Cham (2017)
Combettes, P.L., Wajs, V.R.: Signal recovery by proximal forward-backward splitting. Multiscale Model. Simulat. 4, 1168–1200 (2005)
Tseng, P.: A modified forward-backward splitting method for maximal monotone mappings. SIAM J. Control. Optim. 38, 431–446 (2000)
Malitsky, Y., Tam, M.K.: A forward-backward splitting method for monotone inclusions without cocoercivity. SIAM J. Optim. 30, 1451–1472 (2020)
Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imag. Sci. 2, 183–202 (2009)
Li, G., Pong, T.K.: Douglas-Rachford splitting for nonconvex optimization with application to nonconvex feasibility problems. Math. Program. 159, 371–401 (2016)
Wang, X., Wang, Z.: The exact modulus of the generalized Kurdyka-Łojasiewicz property. Math. Oper. Res. (2021). arXiv:2008.13257, to appear
Attouch, H., Bolte, J., Redont, P., Soubeyran, A.: Proximal alternating minimization and projection methods for nonconvex problems: an approach based on the Kurdyka-Łojasiewicz inequality. Math. Oper. Res. 35, 438–457 (2010)
Attouch, H., Bolte, J., Svaiter, B.F.: Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel Methods. Math. Program. 137, 91–129 (2013)
Banert, S., Boţ, R.I.: A general double-proximal gradient algorithm for dc programming. Math. Program. 178, 301–326 (2019)
Bolte, J., Sabach, S., Teboulle, M., Vaisbourd, Y.: First order methods beyond convexity and Lipschitz gradient continuity with applications to quadratic inverse problems. SIAM J. Optim. 28, 2131–2151 (2018)
Boţ, R.I., Csetnek, E.R.: An inertial Tseng’s type proximal algorithm for nonsmooth and nonconvex optimization problems. J. Optim. Theory Appl. 171, 600–616 (2016)
Li, G., Liu, T., Pong, T.K.: Peaceman-Rachford splitting for a class of nonconvex optimization problems. Comput. Optim. Appl. 68, 407–436 (2017)
Mordukhovich, B.S.: Variational Analysis and Generalized Differentiation I: Basic Theory. Springer-Verlag, Berlin (2006)
Rockafellar, R.T., Wets, R.J.-B.: Variational Analysis. Springer-Verlag, Berlin (1998)
Bolte, J., Sabach, S., Teboulle, M.: Proximal alternating linearized minimization for nonconvex and nonsmooth problems. Math. Program. 146, 459–494 (2014)
Bolte, J., Daniilidis, A., Lewis, A., Shiota, M.: Clarke subgradients of stratifiable functions. SIAM J. Optim. 18, 556–572 (2007)
Boţ, R.I., Nguyen, D.-K.: The proximal alternating direction method of multipliers in the nonconvex setting: convergence analysis and rates. Math. Oper. Res. 45, 682–712 (2020)
Bolte, J., Daniilidis, A., Ley, O., Mazet, L.: Characterizations of Łojasiewicz inequalities: subgradient flows, talweg, convexity. Trans. Am. Math. Soc. 362, 3319–3363 (2010)
Łojasiewicz, S.: Une propriété topologique des sous-ensembles analytiques réels. Les équations aux dérivées partielles 117, 87–89 (1963)
Kurdyka, K.: On gradients of functions definable in o-minimal structures. Annales de l’institut Fourier 48, 769–783 (1998)
Ochs, P., Chen, Y., Brox, T., Pock, T.: iPiano: inertial proximal algorithm for nonconvex optimization. SIAM J. Imag. Sci. 7, 1388–1419 (2014)
Böhm, A., Sedlmayer, M., Csetnek, E. R., Boţ, R. I.: Two steps at a time–taking gan training in stride with Tseng’s method, arXiv:2006.09033, (2020)
Attouch, H., Bolte, J.: On the convergence of the proximal algorithm for nonsmooth functions involving analytic features. Math. Program. 116, 5–16 (2009)
Li, G., Pong, T.K.: Calculus of the exponent of Kurdyka-Łojasiewicz inequality and its applications to linear convergence of first-order methods. Found. Comput. Math. 18, 1199–1232 (2018)
Boţ, R.I., Csetnek, E.R., Nguyen, D.-K.: A proximal minimization algorithm for structured nonconvex and nonsmooth problems. SIAM J. Optim. 29, 1300–1328 (2019)
Chen, C., Pong, T.K., Tan, L., Zeng, L.: A difference-of-convex approach for split feasibility with applications to matrix factorizations and outlier detection. J. Global Optim. 78, 107–136 (2020)
Bauschke, H.H., Luke, D.R., Phan, H.M., Wang, X.: Restricted normal cones and sparsity optimization with affine constraints. Found. Comput. Math. 14, 63–83 (2014)
Lu, Z., Zhang, Y.: Sparse approximation via penalty decomposition methods. SIAM J. Optim. 23, 2448–2478 (2013)
Boţ, R.I., Csetnek, E.R., László, S.C.: An inertial forward-backward algorithm for the minimization of the sum of two nonconvex functions. EURO J. Comput. Optimiz. 4, 3–25 (2016)
Acknowledgements
The authors thank the editor and the reviewers for helpful suggestions and constructive feedback which helped us to improve the presentation of the results. XW and ZW were partially supported by NSERC Discovery Grants.
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
Wang, X., Wang, Z. Malitsky-Tam forward-reflected-backward splitting method for nonconvex minimization problems. Comput Optim Appl 82, 441–463 (2022). https://doi.org/10.1007/s10589-022-00364-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10589-022-00364-0
Keywords
- Generalized concave Kurdyka-Łojasiewicz property
- Proximal mapping
- Malitsky-Tam forward-reflected-backward splitting method
- Merit function
- Global convergence
- Nonconvex optimization