论文标题
通过分布式伪输入培训的稳健不确定性估计
Robust uncertainty estimates with out-of-distribution pseudo-inputs training
论文作者
论文摘要
概率模型通常使用神经网络来控制其预测不确定性。但是，当做出分发（OOD）预测时，神经网络的通常无法控制的外推性能会产生差的不确定性预测。这样，这些模型就不知道他们不知道的东西，它直接限制了他们的鲁棒性W.R.T意外输入。为了解决这个问题，我们建议明确训练不确定性预测变量，其中未获得数据以使其可靠。由于没有数据就无法训练，因此我们提供了在输入空间的信息性低密度区域中生成伪输入的机制，并在实用的贝叶斯框架中展示如何利用这些输入，该框架在模型不确定性上施放了先前的分布。通过整体评估，我们证明，这可以产生不确定性的强大且可解释的预测，同时保留在诸如回归和生成建模之类的各种任务上的最先进的绩效
Probabilistic models often use neural networks to control their predictive uncertainty. However, when making out-of-distribution (OOD)} predictions, the often-uncontrollable extrapolation properties of neural networks yield poor uncertainty predictions. Such models then don't know what they don't know, which directly limits their robustness w.r.t unexpected inputs. To counter this, we propose to explicitly train the uncertainty predictor where we are not given data to make it reliable. As one cannot train without data, we provide mechanisms for generating pseudo-inputs in informative low-density regions of the input space, and show how to leverage these in a practical Bayesian framework that casts a prior distribution over the model uncertainty. With a holistic evaluation, we demonstrate that this yields robust and interpretable predictions of uncertainty while retaining state-of-the-art performance on diverse tasks such as regression and generative modelling
