Convergence Rates of Damped Inertial Dynamics under Geometric Conditions and Perturbations

DOI10.1137/19M1272767zbMath1453.34076MaRDI QIDQ3300770

Aude Rondepierre, Charles Dossal, Unnamed Author

Publication date: 30 July 2020

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

zbMATH Keywords

optimization; rate of convergence; Lyapunov functions; ODEs; Łojasiewicz property

Mathematics Subject Classification ID

65K05: Numerical mathematical programming methods

90C25: Convex programming

90C30: Nonlinear programming

65K10: Numerical optimization and variational techniques

34D05: Asymptotic properties of solutions to ordinary differential equations

Related Items

Convergence Rates of the Heavy Ball Method for Quasi-strongly Convex Optimization, Inertial primal-dual dynamics with damping and scaling for linearly constrained convex optimization problems, Fast convergence of inertial dynamics with Hessian-driven damping under geometry assumptions, A control-theoretic perspective on optimal high-order optimization, Convergence rates of damped inerial dynamics from multi-degree-of-freedom system, Convergence rates of the heavy-ball method under the Łojasiewicz property, Optimal decay rates for semi-linear non-autonomous evolution equations with vanishing damping, Optimal convergence rates for damped inertial gradient dynamics with flat geometries, Fast convergence of inertial gradient dynamics with multiscale aspects, Convergence Rates of Inertial Primal-Dual Dynamical Methods for Separable Convex Optimization Problems

Cites Work

• Unnamed Item
• Unnamed Item
• On the convergence of the iterates of the ``fast iterative shrinkage/thresholding algorithm
• Asymptotic for the perturbed heavy ball system with vanishing damping term
• On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
• On semi- and subanalytic geometry
• From error bounds to the complexity of first-order descent methods for convex functions
• Asymptotic stabilization of inertial gradient dynamics with time-dependent viscosity
• On a second order dissipative ODE in Hilbert spaces with an integrable source term
• On damped second-order gradient systems
• Fast convergence of inertial dynamics and algorithms with asymptotic vanishing viscosity
• The Rate of Convergence of Nesterov's Accelerated Forward-Backward Method is Actually Faster Than $1/k^2$
• A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights
• On the Long Time Behavior of Second Order Differential Equations with Asymptotically Small Dissipation
• On the long time behavior of second order differential equations with asymptotically small dissipation
• Convergence Rates of Inertial Forward-Backward Algorithms
• Asymptotic for a second-order evolution equation with convex potential andvanishing damping term
• Rate of convergence of the Nesterov accelerated gradient method in the subcritical case α ≤ 3
• Asymptotics for a second-order differential equation with nonautonomous damping and an integrable source term
• Optimal Convergence Rates for Nesterov Acceleration
• Some methods of speeding up the convergence of iteration methods