Uncertainty estimation is crucial in safety-critical applications, where robust out-of-distribution (OOD) detection is essential. Traditional Bayesian methods, though effective, are often hindered by high computational demands. As an alternative, Laplace approximation offers a more practical and efficient approach to uncertainty estimation. In this paper, we introduce the Identity Curvature Laplace Approximation (ICLA), a novel method that challenges the conventional posterior covariance formulation by using identity curvature and optimizing prior precision. This innovative design significantly enhances OOD detection performance on well-known datasets such as CIFAR-10, CIFAR-100, and ImageNet, while maintaining calibration scores. We attribute this improvement to the alignment issues between typical feature embeddings and curvature as measured by the Fisher information matrix. Our findings are further supported by demonstrating that incorporating Fisher penalty or sharpness-aware minimization techniques can greatly enhance the uncertainty estimation capabilities of standard Laplace approximation.

翻译：不确定性估计在安全关键应用中至关重要，其中稳健的分布外（OOD）检测是必不可少的。传统的贝叶斯方法虽然有效，但往往受限于高计算需求。作为替代方案，拉普拉斯近似提供了一种更实用高效的不确定性估计方法。本文提出恒等曲率拉普拉斯近似（ICLA），这是一种新颖的方法，它通过使用恒等曲率并优化先验精度，对传统的后验协方差公式提出了挑战。这一创新设计显著提升了在CIFAR-10、CIFAR-100和ImageNet等知名数据集上的OOD检测性能，同时保持了校准分数。我们将此改进归因于典型特征嵌入与由费舍尔信息矩阵度量的曲率之间的对齐问题。我们的发现进一步得到证实，即结合费舍尔惩罚或锐度感知最小化技术可以极大地增强标准拉普拉斯近似的不确定性估计能力。