Abstract
In this paper, we are devoted to the study of a problem proposed in Aujol and Dossal (SIAM J Optim 29:3131–3153, 2019), which concerns the optimal convergence rates for damped inertial gradient dynamics with flat geometries. Fortunately, we find a solution to the problem. More specifically, we obtain an optimal decay rate for the system energy of the second-order differential equation with time-dependent damping in a Hilbert space \({\mathcal {H}}\)
where \(F : {\mathcal {H}} \rightarrow R\) is a differentiable convex function possessing at least one minimizer and \(\gamma (t)=\alpha /t\) with \(\alpha >0.\) It is known that this system, with the time-dependent damping coefficient \(\gamma (t)\), models a nonlinear oscillator with viscous damping, and is associated with the Nesterov acceleration scheme, FISTA, or the accelerated gradient method in the area of numerical optimization.
We’re sorry, something doesn't seem to be working properly.
Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.
Change history
22 July 2023
A Correction to this paper has been published: https://doi.org/10.1007/s00245-023-10026-0
References
Apidopoulos, V., Aujol, J.F., Dossal, C.: The differential inclusion modeling FISTA algorithm and optimality of convergence rate in the case \(b\le 3\). SIAM J. Optim. 28, 551–574 (2018)
Attouch, H., Cabot, A., Chbani, Z., Riahi, H.: Rate of convergence of inertial gradient dynamics with time-dependent damping coefficient. Evol. Equ. Control Theory 7, 353–371 (2018)
Attouch, H., Chbani, Z., Peypouquet, J., Redont, P.: Fast convergence of inertial dynamics and algorithms with asymptotic vanishing viscosity. Math. Program. 168, 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 (2019)
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., Fadili, J., Riahi, H.: First-order optimization algorithms via inertial systems with Hessian driven damping. Math. Program. 193(Ser. A), 113–155 (2022)
Aujol, J.F., Dossal, C.: A. Rondepierre, Optimal convergence rates for Nesterov acceleration. SIAM J. Optim. 29, 3131–3153 (2019)
Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imaging Sci. 2, 183–202 (2009)
Bezerra, F.D.M., Carvalho, A.N., Cholewa, J.W., Nascimento, M.J.D.: Parabolic approximation of damped wave equations via fractional powers: fast growing nonlinearities and continuity of the dynamics. J. Math. Anal. Appl. 450(1), 377C – 405 (2017)
Bolte, J., Nguyen, T., Peypouquet, J., Suter, B.: From error bounds to the complexity of first-order descent methods for convex functions. Math. Program. 165, 471–507 (2017)
Diagana, T.: Semilinear Evolution Equations and Their Applications. Springer, Cham (2018)
Jendoubi, M.A., May, R.: Asymptotics for a second-order differential equation with nonautonomous damping and an integrable source term. Appl. Anal. 94, 435–443 (2015)
Jin, K.P., Liang, J., Xiao, T.J.: Uniform stability of semilinear wave equations with arbitrary local memory effects versus frictional dampings. J. Differ. Equ. 266, 7230–7263 (2019)
Luo, J.R., Xiao, T.J.: Decay rates for second order evolution equations in Hilbert spaces with nonlinear time-dependent damping. Evol. Equ. Control Theory 9, 359–373 (2020)
Luo, J.R., Xiao, T.J.: Optimal energy decay rates for abstract second order evolution equations with non-autonomous damping. ESAIM Control Optim. Calc. Var. 27 (2021)
Luo, J.R., Xiao, T.J.: Decay rates for semilinear wave equations with vanishing damping and Neumann boundary conditions. Math. Methods Appl. Sci. 44, 303–314 (2021)
May, R.: Asymptotic for a second-order evolution equation with convex potential and vanishing damping term. Turk. J. Math. 41, 681–685 (2017)
May, R.: On the convergence of the continuous gradient projection method. Optimization 68, 1791–1806 (2019)
Nesterov, Y.: A method of solving a convex programming problem with convergence rate \(o(1/k^2)\). Sov. Math. Dokl. 27, 372–376 (1983)
Polyak, B.T.: Some methods of speeding up the convergence of iteration methods. Comput. Math. Math. Phys. 4, 1–17 (1964)
Sebbouh, O., Dossal, C.H., Rondepierre, A.: Convergence rates of damped inertial dynamics under geometric conditions and perturbations. SIAM J. Optim. 30, 1850–1877 (2020)
Su, W., Boyd, S., Cand\(\grave{{\rm e}}\)s, E.J.: A differential equation for modeling Nesterov’s accelerated gradient method: theory and insights. J. Mach. Learn. Res. 17, 1–43 (2016)
Acknowledgements
The authors would like to thank the referee very much for his/her professional and valuable comments and suggestions. The work was supported partly by the NSF of China (Grant Numbers 11947004, 11831011) and the Shanghai Key Laboratory for Contemporary Applied Mathematics (Grant Number 08DZ2271900).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The original article has been revised due to an error in copyright line.
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
Luo, JR., Xiao, TJ. Optimal Convergence Rates for Damped Inertial Gradient Dynamics with Flat Geometries. Appl Math Optim 87, 53 (2023). https://doi.org/10.1007/s00245-023-09966-4
Accepted:
Published:
DOI: https://doi.org/10.1007/s00245-023-09966-4