*Not just for reducing complexity also Improves Generalization
*Augments sparse vectors (SVM) with Sparse Dimensions
*Is possible jointly with parameter estimation.
*Can be done discriminatively.
Maximum Entropy Discrimination:
Combines probabilistic methods (and
extensions) in discriminative framework
Feasible MED Extensions & Applications:
Latent variables, various priors, missing labels,
structure estimation, anomaly detection.
Feature selection, regression, latent transformations,
multi-class classification, exponential family.