Qu'est-ce que « Decision-focused learning, differentiable optimisation layer » ?

Decision-focused learning trains a forecast by the quality of the decisions made with it: the forecast is passed through the optimiser and the loss is computed on the decision’s outcome (Donti, Amos and Kolter, 2017). It needs a differentiable optimisation layer: an optimiser whose solution can be differentiated with respect to its inputs, in closed form as here, by implicit differentiation of the optimality conditions of a quadratic programme (Amos and Kolter, 2017), or for general convex problems (Agrawal and co-authors, 2019).