Provably faster gradient descent via long steps

Recommendations

Factor-\(\sqrt{2}\) acceleration of accelerated gradient methods
A note on the optimal convergence rate of descent methods with fixed step sizes for smooth strongly convex functions
On the convergence analysis of the optimized gradient method
scientific article; zbMATH DE number 7306906
The exact worst-case convergence rate of the gradient method with fixed step lengths for \(L\)-smooth functions

Cites work

A relaxed interior point method for low-rank semidefinite programming problems with applications to matrix completion
Accelerated proximal point method for maximally monotone operators
An elementary approach to tight worst case complexity analysis of gradient based methods
An optimal gradient method for smooth strongly convex minimization
An optimal-storage approach to semidefinite programming using approximate complementarity
Branch-and-bound performance estimation programming: a unified methodology for constructing optimal optimization methods
Convex optimization algorithms
Efficient first-order methods for convex minimization: a constructive approach
Exact worst-case performance of first-order methods for composite convex optimization
Exploiting low-rank structure in semidefinite programming by approximate operator splitting
Implicit Regularity and Linear Convergence Rates for the Generalized Trust-Region Subproblem
On Richardson's Method for Solving Linear Systems with Positive Definite Matrices
On the convergence rate of the Halpern-iteration
On the worst-case complexity of the gradient method with exact line search for smooth strongly convex functions
Operator splitting performance estimation: tight contraction factors and optimal parameter selection
Optimal Convergence Rates for the Proximal Bundle Method
Optimal complexity and certification of Bregman first-order methods
Optimized first-order methods for smooth convex minimization
Optimizing the efficiency of first-order methods for decreasing the gradient of smooth convex functions
Ordering of the iterative parameters in the cyclical Chebyshev iterative method
Performance of first-order methods for smooth convex minimization: a novel approach
Principled analyses and design of first-order methods with inexact proximal operators
Revisiting Spectral Bundle Methods: Primal-Dual (Sub)linear Convergence Rates
Scalable semidefinite programming
Smooth strongly convex interpolation and exact worst-case performance of first-order methods
Tight sublinear convergence rate of the proximal point algorithm for maximal monotone inclusion problems
Worst-case convergence analysis of inexact gradient and Newton methods through semidefinite programming performance estimation

Cited in

(1)

Algebraic conditions for stability in Runge-Kutta methods and their certification via semidefinite programming

This page was built for publication: Provably faster gradient descent via long steps

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6579999)