| Class | Description |
|---|---|
| GLM |
Created by tomasnykodym on 8/27/14.
|
| GLM.BetaConstraint | |
| GLM.GLMGradientInfo | |
| GLM.GLMGradientSolver |
Gradient and line search computation for L_BFGS and also L_BFGS solver wrapper (for ADMM)
|
| GLM.GLMTaskInfo |
Encapsulates state of the computation.
|
| GLM.GramSolver |
Created by tomasnykodym on 3/30/15.
|
| GLM.LBFGS_ProximalSolver | |
| GLM.ProximalGradientInfo | |
| GLM.ProximalGradientSolver |
Simple wrapper around gradient computation, adding proximal penalty
|
| GLMModel |
Created by tomasnykodym on 8/27/14.
|
| GLMModel.GLMOutput | |
| GLMModel.GLMParameters | |
| GLMModel.Submodel | |
| GLMTask |
All GLM related distributed tasks:
YMUTask - computes response means on actual datasets (if some rows are ignored - e.g ignoring rows with NA and/or doing cross-validation)
GLMGradientTask - computes gradient at given Beta, used by L-BFGS, for KKT condition check
GLMLineSearchTask - computes residual deviance(s) at given beta(s), used by line search (both L-BFGS and IRLSM)
GLMIterationTask - used by IRLSM to compute Gram matrix and response t(X) W X, t(X)Wz
|
| GLMTask.GLMCoordinateDescentTask | |
| GLMTask.GLMIterationTask |
One iteration of glm, computes weighted gram matrix and t(x)*y vector and t(y)*y scalar.
|
| GLMTask.LBFGS_LogisticGradientTask |
Tassk with simplified gradient computation for logistic regression (and least squares)
Looks like
|
| GLMValidation |
Class for GLMValidation.
|
| Enum | Description |
|---|---|
| GLMModel.GLMParameters.Family | |
| GLMModel.GLMParameters.Link | |
| GLMModel.GLMParameters.Solver |