I'm exploring follow-the-regularized-leader FTRL proximal gradient descent: paper, reference implementation.
Everywhere FTRL is mentioned, the loss surface for the gradient decent is the LogLoss
, and the model for prediction is Logistic regression
.
Can I use the same algorithm for a linear least squares model? I have a problem I want to model with a linear model
and define the loss by least squares
, and then do FTRL to find the optimal solution - do you see any problem with that?
Thanks.