In this paper, we critically evaluate Bayesian methods for uncertainty estimation in deep learning, focusing on the widely applied Laplace approximation and its variants. Our findings reveal that the conventional method of fitting the Hessian matrix negatively impacts out-of-distribution (OOD) detection efficiency. We propose a different point of view, asserting that focusing solely on optimizing prior precision can yield more accurate uncertainty estimates in OOD detection while preserving adequate calibration metrics. Moreover, we demonstrate that this property is not connected to the training stage of a model but rather to its intrinsic properties. Through extensive experimental evaluation, we establish the superiority of our simplified approach over traditional methods in the out-of-distribution domain.

本研究评估了贝叶斯方法在深度学习中用于不确定性估计的方法，重点关注广泛应用的Laplace近似及其变体。我们的研究发现，传统的拟合Hessian矩阵的方法对于处理超出分布的检测效率产生了负面影响。我们提出了一种不同的观点，认为仅关注优化先验精度可以在超出分布检测中产生更准确的不确定性估计，并保持适度的校准度。此外，我们证明了这种特性与模型的训练阶段无关，而是与其内在性质相关。通过广泛的实验评估，我们证实了我们简化方法在超出分布领域中优于传统方法的优越性。

揭示拉普拉斯近似用于不确定性估计的经验病理