Current uncertainty quantification is memory and compute expensive, which hinders practical uptake. To counter, we develop Sketched Lanczos Uncertainty (SLU): an architecture-agnostic uncertainty score that can be applied to pre-trained neural networks with minimal overhead. Importantly, the memory use of SLU only grows logarithmically with the number of model parameters. We combine Lanczos' algorithm with dimensionality reduction techniques to compute a sketch of the leading eigenvectors of a matrix. Applying this novel algorithm to the Fisher information matrix yields a cheap and reliable uncertainty score. Empirically, SLU yields well-calibrated uncertainties, reliably detects out-of-distribution examples, and consistently outperforms existing methods in the low-memory regime.

翻译：当前的不确定性量化方法在内存和计算上成本高昂，这阻碍了其实际应用。为此，我们开发了草绘兰索斯不确定性评分：一种与架构无关的不确定性评分方法，可以以最小的开销应用于预训练的神经网络。重要的是，SLU的内存使用量仅随模型参数数量呈对数增长。我们将兰索斯算法与降维技术相结合，以计算矩阵主要特征向量的草图。将这一新颖算法应用于费舍尔信息矩阵，可产生廉价且可靠的不确定性评分。实证表明，SLU能产生校准良好的不确定性，可靠地检测分布外样本，并在低内存环境下持续优于现有方法。