How to Select an Objective Function Using Information Theory
How to Select an Objective Function Using Information Theory
Abstract In machine learning or scientific computing, model performance is measured with an objective function. But why choose one objective over another? According to the informationātheoretic paradigm, the ābestā objective function is whichever minimizes information loss. To evaluate different objectives, transform them into likelihoods. The ratios of these likelihoods represent ā¦