Convergence rates for an inertial algorithm of gradient type associated to a smooth nonconvex minimization

2018/11/22 by László, Szilárd Csaba
#65K10 #90C26 #90C30 #FOS: Mathematics #Functional Analysis (math.FA)

paper · doi:10.48550/arxiv.1811.09616

Abstract

We investigate an inertial algorithm of gradient type in connection with the minimization of a nonconvex differentiable function. The algorithm is formulated in the spirit of Nesterov's accelerated convex gradient method. We prove some abstract convergence results which applied to our numerical scheme allows us to show that the generated sequences converge to a critical point of the objective function, if a regularization of the objective function satisfies the Kurdyka-Łojasiewicz property. Further, we provide convergence rates for the generated sequences and the objective function values formulated in terms of the Łojasiewicz exponent. Finally, we obtain sublinear convergence rates for the objective function values in the iterates in the case when the objective function is convex.

Related

• Convergence rates for an inertial algorithm of gradient type associated\n to a smooth nonconvex minimization
• Rate of convergence of the Nesterov accelerated gradient method in the subcritical case α≤ 3
• Accelerated Gradient Methods via Inertial Systems with Hessian-driven Damping
• A proximal-gradient inertial algorithm with Tikhonov regularization: strong convergence to the minimal norm solution
• Convex optimization via inertial algorithms with vanishing Tikhonov regularization: fast convergence to the minimum norm solution