Abstract
The class of convex–concave bilinear saddle point problems encompasses many important convex optimization models arising in a wide array of applications. The most of existing primal–dual dynamical systems for saddle point problems are based on first order ordinary differential equations (ODEs), which only own the \({\mathcal {O}}(1/t)\) convergence rate in the convex case, and fast convergence rate analysis always requires some additional assumption such as strong convexity. In this paper, based on second order ODEs, we consider a general inertial primal–dual dynamical system, with damping, scaling and extrapolation coefficients, for a convex–concave bilinear saddle point problem. By the Lyapunov analysis approach, under appropriate assumptions, we investigate the convergence rates of the primal–dual gap and velocities, and the boundedness of the trajectories for the proposed dynamical system. With special parameters, our results can recover the Polyak’s heavy ball acceleration scheme and Nesterov’s acceleration scheme. We also provide numerical examples to support our theoretical claims.
Similar content being viewed by others
References
Attouch, H., Boţ, R.I., Csetnek, E.R.: Fast optimization via inertial dynamics with closed-loop damping. J. Eur. Math. Soc. 25(5), 1985–2056 (2022)
Attouch, H., Cabot, A., Chbani, Z., Riahi, H.: Rate of convergence of inertial gradient dynamics with time-dependent viscous damping coefficient. Evol. Equ. Control Theory 7(3), 353–371 (2018)
Attouch, H., Chbani, Z., Fadili, J., Riahi, H.: Fast convergence of dynamical ADMM via time scaling of damped inertial dynamics. J. Optim. Theory Appl. 193, 704–736 (2022)
Attouch, H., Chbani, Z., Peypouquet, J., Redont, P.: Fast convergence of inertial dynamics and algorithms with asymptotic vanishing viscosity. Math. Program. 168(1), 123–175 (2018)
Attouch, H., Chbani, Z., Riahi, H.: Rate of convergence of the Nesterov accelerated gradient method in the subcritical case \(\alpha \le 3\). ESAIM Control Optim. Calc. Var. 25, Article number: 2 (2019)
Balhag, A., Chbani, Z., Riahi, H.: Linear convergence of inertial gradient dynamics with constant viscous damping coefficient and time-dependent rescaling parameter. Available at HAL Id: https://hal.science/hal-02610699 (2020)
Boţ, R.I., Csetnek, E.R.: Second order forward-backward dynamical systems for monotone inclusion problems. SIAM J. Control Optim. 54(3), 1423–1443 (2016)
Boţ, R.I., Csetnek, E.R., László, S.C.: A primal-dual dynamical approach to structured convex minimization problems. J. Differ. Equ. 269(12), 10717–10757 (2020)
Boţ, R.I., Csetnek, E.R., Nguyen, D.K.: Fast augmented Lagrangian method in the convex regime with convergence guarantees for the iterates. Math. Program. 200(1), 147–197 (2023)
Boţ, R.I., Csetnek, E.R., Sedlmayer, M.: An accelerated minimax algorithm for convex-concave saddle point problems with nonsmooth coupling function. Comput. Optim. Appl. 86, 925–966 (2023)
Boţ, R.I., Nguyen, D.K.: Improved convergence rates and trajectory convergence for primal-dual dynamical systems with vanishing damping. J. Differ. Equ. 303, 369–406 (2021)
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)
Chavdarova, T., Jordan, M.I., Zampetakis, M.: Last-iterate convergence of saddle point optimizers via high-resolution differential equations. In: NeurIPS Workshop on Optimization for Machine Learning (2021)
Cherukuri, A., Gharesifard, B., Cortès, J.: Saddle-point dynamics: conditions for asymptotic stability of saddle points. SIAM J. Control Optim. 55(1), 486–511 (2017)
Cherukuri, A., Mallada, E., Low, S., Cortés, J.: The role of convexity in saddle-point dynamics: Lyapunov function and robustness. IEEE Trans. Automat. Control 63(8), 2449–2464 (2019)
Ding, D., Jovanović, M.R.: Global exponential stability of primal–dual gradient flow dynamics based on the proximal augmented Lagrangian. In: 2019 American Control Conference (ACC), pp. 3414–3419 (2019)
Fan, Q., Jiao, Y., Lu, X.: A primal dual active set algorithm with continuation for compressed sensing. IEEE Trans. Signal Process. 62(23), 6276–6285 (2014)
Fazlyab, M., Koppel, A., Preciado, V.M., Ribeiro, A.: A variational approach to dual methods for constrained convex optimization. In: 2017 American Control Conference (ACC), pp. 5269–5275 (2017)
Garg, K., Panagou, D.: Fixed-time stable gradient flows: applications to continuous-time optimization. IEEE Trans. Automat. Control 66(5), 2002–2015 (2021)
Haraux, A.: Systemes dynamiques dissipatifs et applications. Elsevier Masson, Paris (1991)
Hassan-Moghaddam S., Jovanović, M.R.: Proximal gradient flow and Douglas–Rachford splitting dynamics: global exponential stability via integral quadratic constraints. Automatica 123, Article number: 109311 (2021)
He, X., Hu, R., Fang, Y.P.: Convergence rates of inertial primal-dual dynamical methods for separable convex optimization problems. SIAM J. Control Optim. 59(5), 3278–3301 (2021)
He, X., Hu, R., Fang, Y. P.: Fast primal-dual algorithm via dynamical system for a linearly constrained convex optimization problem. Automatica 146, Article number: 110547 (2022)
He, X., Hu, R., Fang, Y.P.: Inertial primal-dual dynamics with damping and scaling for linearly constrained convex optimization problems. Appl. Anal. 102(15), 4114–4139 (2023)
He, X., Hu, R., Fang, Y.P.: “Second-order primal’’ + “first-order dual’’ dynamical systems with time scaling for linear equality constrained convex optimization problems. IEEE Trans. Automat. Control 67(8), 4377–4383 (2022)
He, B., Yuan, X.: Convergence analysis of primal-dual algorithms for a saddle-point problem: from the contraction perspective. SIAM J. Imaging Sci. 5(1), 119–149 (2012)
Hulett D.A., Nguyen, D.K.: Time rescaling of a primal-dual dynamical system with asymptotically vanishing damping. Appl. Math. Optim. 88, Article number: 27 (2023)
Jiang, F., Cai, X., Wu, Z., Han, D.: Approximate first-order primal-dual algorithms for saddle point problems. Math. Comp. 90(329), 1227–1262 (2021)
Liang, S., Yin, G.: Exponential convergence of distributed primal-dual convex optimization algorithm without strong convexity. Automatica 105, 298–306 (2019)
Lin, Z., Li, H., Fang, C.: Accelerated Optimization for Machine Learning. Springer, Singapore (2020)
Lu, H.: An \(O(s^r)\)-resolution ODE framework for understanding discrete-time algorithms and applications to the linear convergence of minimax problems. Math. Program. 194(1), 1061–1112 (2022)
Luo, H.: A primal-dual flow for affine constrained convex optimization. ESAIM Control Optim. Calc. Var. 28, Article Number: 33 2022
Malitsky, Y., Pock, T.: A first-order primal-dual algorithm with linesearch. SIAM J. Optim. 28(1), 411–432 (2018)
Nesterov, Y.: Introductory Lectures on Convex Optimization: A Basic Course. Springer, New York (2003)
Nesterov, Y.: A method of solving a convex programming problem with convergence rate \({\cal{O} }(1/k^2)\). Sov. Math. Dokl. 27(2), 372–376 (1983)
Polyak, B.T.: Some methods of speeding up the convergence of iteration methods. USSR Comput. Math. Math. Phys. 4(5), 1–17 (1964)
Schmidt, M., Fung, G., Rosales, R.: Fast optimization methods for L1 regularization: a comparative study and two new approaches. In: European Conference on Machine Learning, pp. 286–297. Springer (2007)
Su, W., Boyd, S., Candés, E.J.: A differential equation for modeling Nesterov’s accelerated gradient method: theory and insights. J. Mach. Learn. Res. 17(153), 5312–5354 (2016)
Sun, T., Yin, P., Li, D., Huang, C., Guan, L., Jiang, H.: Non-ergodic convergence analysis of heavy-ball algorithms. Proc. AAAI Conf. Artif. Intell. 33(1), 5033–5040 (2019)
Tang, Y., Qu, G., Li, N.: Semi-global exponential stability of augmented primal-dual gradient dynamics for constrained convex optimization. Syst. Control Lett. 144, Article Number: 104754 (2020)
Wibisono, A., Wilson, A.C., Jordan, M.I.: A variational perspective on accelerated methods in optimization. Proc. Natl. Acad. Sci. U.S.A. 113(47), E7351–E7358 (2016)
Wilson, A.C., Recht, B., Jordan, M.I.: A Lyapunov analysis of accelerated methods in optimization. J. Mach. Learn. Res. 22(113), 1–34 (2021)
Zeng, X., Lei, J., Chen, J.: Dynamical primal-dual accelerated method with applications to network optimization. IEEE Trans. Automat. Control 68(3), 1760–1767 (2023)
Zeng, X., Lei, J., Chen, J.: Accelerated first-order continuous-time algorithm for solving convex-concave bilinear saddle point problem. IFAC-PapersOnLine 53(2), 7362–7367 (2020)
Acknowledgements
The authors are thankful to two anonymous reviewers for their remarks and suggestions which have improved the quality of the paper.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
No potential conflict of interest was reported by the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
He, X., Hu, R. & Fang, Y. A Second Order Primal–Dual Dynamical System for a Convex–Concave Bilinear Saddle Point Problem. Appl Math Optim 89, 30 (2024). https://doi.org/10.1007/s00245-023-10102-5
Accepted:
Published:
DOI: https://doi.org/10.1007/s00245-023-10102-5
Keywords
- Second order primal–dual dynamical system
- Bilinear saddle point problem
- Lyapunov analysis
- Convergence rate