论文标题
学习随机扰动的结构化预测指标，以最小化直接损失
Learning Randomly Perturbed Structured Predictors for Direct Loss Minimization
论文作者
论文摘要
直接损失最小化是学习预测因子对结构化标签空间的流行方法。这种方法在计算上具有吸引力，因为它可以用优化取代集成，并允许使用损失扰动的预测在深网中传播梯度。最近，该技术扩展到生成模型，同时引入了一个随机的预测指标，该预测值从随机扰动的分数函数中采样结构。在这项工作中，我们了解了这些随机结构化预测指标的方差，并表明它在结构化预测中的学习分数函数和随机噪声之间可以更好地平衡。我们从经验上证明了在结构化离散空间中学习信号和随机噪声之间平衡的有效性。
Direct loss minimization is a popular approach for learning predictors over structured label spaces. This approach is computationally appealing 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, while introducing a randomized predictor that samples a structure from a randomly perturbed score function. In this work, we learn the variance of these randomized structured predictors and show that it balances better between the learned score function and the randomized noise in structured prediction. We demonstrate empirically the effectiveness of learning the balance between the signal and the random noise in structured discrete spaces.
