Matrix Factorization In Matlab using Stochastic Gradient Descent
显示 更早的评论
I have to factorize Matrix R[m*n] to two low-rank Matrices (U[K*m] and V[K*n]), I do this for predicting missing values of R by U and V.
The problem is, for factorizing R I can't use Matlab factorization methods, so I have to work on objective function which minimizes the sum-of-squared-errors for enhancing factorization accuracy:
details are shown below:
My Question in this post is how to minimize function F in Matlab Using Stochastic Gradient Descent method to decompose R into U and V matrices.
1 个评论
Matt J
2013-10-7
Since your function is not continuous/differentiable (because I_ij is not), I wonder whether any kind of gradient method applies.
How large are R, U, ad V typically. You might be able to use the genetic algorithm ga() in the Global Optimization Toolbox.
回答（0 个）
类别
在 帮助中心 和 File Exchange 中查找有关 Get Started with MATLAB 的更多信息
产品
2013-10-7
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
