Accelerated Objective Gap and Gradient Norm Convergence for Gradient Descent via Long Steps

A method for solving the convex programming problem with convergence rate o ⁡ ( 1 / k 2 ) o(1/k^{2})

Yurii Nesterov · 1983

Earlier work this paper cites.

Problem Complexity and Method Efficiency in Optimization

A. Nemirovski and D. Yudin · 1983

Earlier work this paper cites.

Performance of first-order methods for smooth convex minimization: a novel approach

Yoel Drori and Marc Teboulle · 2012

Earlier work this paper cites.

Smooth strongly convex interpolation and exact worst-case performance of first-order methods

Adrien B. Taylor, Julien M. Hendrickx, and François Glineur · 2015

Earlier work this paper cites.

Smooth strongly convex interpolation and exact worst-case performance of first-order methods

Adrien Taylor, Julien Hendrickx, and François Glineur · 2017

Earlier work this paper cites.

Exact worst-case performance of first-order methods for composite convex optimization

Adrien Taylor, Julien Hendrickx, and François Glineur · 2017

Earlier work this paper cites.

Greed, hedging, and acceleration in convex optimization

Jason Altschuler · 2018

Earlier work this paper cites.

Lectures on Convex Optimization

Yurii Nesterov · 2018

Cited alongside, same era.

Performance estimation of the gradient method with fixed arbitrary step sizes

Antoine Daccache · 2019

Cited alongside, same era.

Optimizing the efficiency of first-order methods for decreasing the gradient of smooth convex functions

Donghwan Kim and Jeffrey A. Fessler · 2021

Cited alongside, same era.

An elementary approach to tight worst case complexity analysis of gradient based methods

Marc Teboulle and Yakov Vaisbourd · 2022

Cited alongside, same era.

Worst-case functions for the gradient method with fixed variable step sizes

Diego Eloi · 2022

Cited alongside, same era.

Accelerated gradient descent via long steps, 2023

Benjamin Grimmer, Kevin Shu, and Alex L. Wang · 2023

Cited alongside, same era.

Provably Faster Gradient Descent via Long Steps

Original

B. Grimmer · 2023

Later among the works it cites.

Acceleration by stepsize hedging i: Multi-step descent and the silver stepsize schedule, 2023

Jason M. Altschuler and Pablo A. Parrilo · 2023

Later among the works it cites.

Acceleration by stepsize hedging ii: Silver stepsize schedule for smooth convex optimization, 2023

Jason M. Altschuler and Pablo A. Parrilo · 2023

Later among the works it cites.

Time-reversed dissipation induces duality between minimizing gradient norm and function value, 2023

Jaeyeon Kim, Asuman Ozdaglar, Chanwoo Park, and Ernest K. Ryu · 2023

Later among the works it cites.

Mathematica, Version 13.3

Wolfram Research, Inc · 2023

Later among the works it cites.

On averaging and extrapolation for gradient descent, 2024