Fairness and discrimination, PhD Course, #5 Machine learning models

For the fifth course, we will discuss machine learning and standard techniques used to get predictive models, and to assess accuracy of those models. GLM (possibly constrained) Classically, we use a penalized version of least squares (but this can be adapted to GLMs, when penalizing the negative log-likelihood).  Because of Karush–Kuhn–Tucker conditions, having a constraint on the parameter is equivalent to the following penalized problem, when the constraint is on the norm of , We can also consider the norm of , Those two … <a href=“https://freakonometrics.hypotheses.org/69911" …