Uncertainty estimation (UE) techniques -- such as the Gaussian process (GP), Bayesian neural networks (BNN), Monte Carlo dropout (MCDropout) -- aim to improve the interpretability of machine learning models by assigning an estimated uncertainty value to each of their prediction outputs. However, since too high uncertainty estimates can have fatal consequences in practice, this paper analyzes the above techniques. Firstly, we show that GP methods always yield high uncertainty estimates on out of distribution (OOD) data. Secondly, we show on a 2D toy example that both BNNs and MCDropout do not give high uncertainty estimates on OOD samples. Finally, we show empirically that this pitfall of BNNs and MCDropout holds on real world datasets as well. Our insights (i) raise awareness for the more cautious use of currently popular UE methods in Deep Learning, (ii) encourage the development of UE methods that approximate GP-based methods -- instead of BNNs and MCDropout, and (iii) our empirical setups can be used for verifying the OOD performances of any other UE method. The source code is available at https://github.com/epfml/uncertainity-estimation.
翻译:不确定估计(UE)技术 -- -- 例如Gausian进程(GP)、Bayesian神经网络(BNN)、蒙特卡洛辍学(MCDropout) -- -- 旨在通过给机器学习模型的每个预测产出分配估计的不确定性值来改进机器学习模型的解释性。然而,由于不确定性估计过高可能在实践中产生致命后果,本文分析上述技术。首先,我们表明GP方法总是对分发数据(OOOD)产生高度不确定性估计。第二,我们在一个2D小例子中显示,BNN和MCDropout对OOD样本的不确定性估计并不高。最后,我们从经验上表明,BNN和MCDropout的这一陷阱也存在于真实的世界数据集中。我们的见解(i)提高了对在深层学习中更谨慎地使用目前流行的UE方法的认识,(ii)鼓励发展接近GP-方法的UE方法 -- -- 而不是BNS和MCDropout,以及(iii)我们的经验性设置可用于核查OD的 OOD性表现。 AM/Seprestimm 方法的源码。