... 294 3.3 Statistical Learning cost We now discuss Comet’s statistical learning component 3.3.1 cost h1, j (vj ) The General Learning Problem Given a set of d features, the goal of the statistical ... ), with wj,i = h1,j (vj,i ) being the value of the transformed jth feature for query qi In statistical- learning terminology, the transformation of vj to wj “linearizes” the jth feature with ... greedy forward stepwise-regression algorithm The resulting model is of the “generalized additive” form Transform Regression For reasons discussed previously, we use the recentlyproposed transform...