Convergence of Exponentiated Gradient Algorithms
This paper studies three related algorithms: the (traditional) gradient descent (GD) algorithm, the exponentiated gradient algorithm with positive and negative weights (EG± algorithm), and the exponentiated gradient algorithm with unnormalized positive a
|Collections||ANU Research Publications|
|Source:||IEEE Transactions on Signal Processing|
|01_Hill_Convergence_of_Exponentiated_2001.pdf||151.91 kB||Adobe PDF||Request a copy|
|02_Hill_Convergence_of_Exponentiated_2001.pdf||963.35 kB||Adobe PDF||Request a copy|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.