The iteration-stability bound claimed for the explicit-implicit Euler discretization of the Euler-Lagrange acceleration ODE is not proven and is false for some parameter values permitted by the theorem.
Explicit Stabilised Gradient Descent for Faster Strongly Convex Optimisation
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
This paper introduces the Runge-Kutta Chebyshev descent method (RKCD) for strongly convex optimisation problems. This new algorithm is based on explicit stabilised integrators for stiff differential equations, a powerful class of numerical schemes that avoid the severe step size restriction faced by standard explicit integrators. For optimising quadratic and strongly convex functions, this paper proves that RKCD nearly achieves the optimal convergence rate of the conjugate gradient algorithm, and the suboptimality of RKCD diminishes as the condition number of the quadratic function worsens. It is established that this optimal rate is obtained also for a partitioned variant of RKCD applied to perturbations of quadratic functions. In addition, numerical experiments on general strongly convex problems show that RKCD outperforms Nesterov's accelerated gradient descent.
citation-role summary
citation-polarity summary
fields
math.OC 1years
2019 1verdicts
REJECT 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
On the stability of optimization algorithms given by discretizations of the Euler-Lagrange ODE
The iteration-stability bound claimed for the explicit-implicit Euler discretization of the Euler-Lagrange acceleration ODE is not proven and is false for some parameter values permitted by the theorem.