arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.05890cs.LGstat.ML
收藏

具有分布外伪输入训练的鲁棒不确定性估计

Robust uncertainty estimates with out-of-distribution pseudo-inputs training

electricityMap(electricityMap公司)

Pierre Segonne, Yevgen Zainchkovskyy, Søren Hauberg

摘要:

概率模型通常使用神经网络来控制其预测的不确定性。然而,当进行分布外(OOD)预测时,神经网络的通常不可控的外推性质产生差的不确定性预测。这样的模型就不知道他们不知道什么,这直接限制了他们对意外输入的鲁棒性。为了解决这个问题,我们建议显式地训练不确定性预测,我们没有给出数据,使其可靠。由于没有数据就不能训练,我们提供了在输入空间的信息低密度区域生成伪输入的机制,并展示了如何在一个实际的贝叶斯框架中利用这些机制,该框架在模型的不确定性上投射先验分布。通过全面的评估,我们证明了这会产生强大的和可解释的不确定性预测,同时在回归和生成建模等各种任务上保持最先进的性能

英文摘要:

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

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑