Implicit regularization:

Problem Setting for Question Assume we have a training dataset { (Xi, yi) )i=1, where x; E Rd is the input vector and yi E { +1 } is the label, i = 1, ..., n. For a linear model f (x) = w x with parameter w E Rd, consider the following empirical risk minimization problem n L(W) := Ce((w, xi), yi) (1) i=1Choose the exponential loss ((y, y) = exp(-yy) in (1). Prove that that || VC(w) ||2 2 76(w), for any w E Rd, where y = max min yi (w, xi) . |/ w/ /2=11