Abstract: Direct loss minimization is a popular approach for learning predictors over structured label spaces. This approach is computationally ap-pealing as it replaces integration with optimization and allows to propagate gradients in a deep net using loss-perturbed prediction. Recently, this technique was extended to generative models, by introducing a randomized predictor that samples a structure from a randomly perturbed score function. In this work, we interpolate between these techniques by learning the variance of randomized structured predictors as well as their mean, in order to balance between the learned score function and the randomized noise.
We extend the direct optimization technique to
learn this balance, in a high-dimensional structured label setting.
We demonstrate empirically the effectiveness of learning this balance in two diverse structured discrete spaces.