Consider a binary-classification problem where the goal is to predict a label y {0, 1}, given an input x Rd. A method that you can use for this task is logistic regression. In logistic regression, we model the log-odds as a linear function of the data and find weights to maximize the likelihood of our data under the resulting model. Recall that a linear function (f ) takes the form f (x) = wx + c with c R and w, x Rn. Recall the log-likelihood for a logistic-regression model can be written as