Skip to content

Repository files navigation

Adaptive accelerated gradient descent

This code implements the gradient descent algorithms gradient descent with constant stepsize, Nesterov accelerated gradien descent, AdaNAG_G (developed by Jaewook J. Suh, Shiqian Ma in "An Adaptive and Parameter-Free Nesterov’s Accelerated Gradient Method for Convex Optimization") and the newly developed algorithm AdaAGM (Zepeng Wang, Juan Peypouquet in "Adaptive accelerated gradient method for smooth convex optimization").

These methods are tested on the model problems logistic regression and least squares using real world and random data.

About

Implementation of AdaAGM and Testing of different gradient descent methods

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages