论文标题
神经合奏搜索不确定性估计和数据集偏移
Neural Ensemble Search for Uncertainty Estimation and Dataset Shift
论文作者
论文摘要
与独立网络相比，在准确性，不确定性校准和对数据集偏移的鲁棒性方面，神经网络的集合获得了卓越的性能。 \ emph {deep emembles}，一种不确定性估计的最新方法，仅集合的随机初始化\ emph {fixed}架构。取而代之的是，我们提出了两种使用\ emph {varying}体系结构自动构建合奏的方法，它们隐含地权衡各个体系结构的优势，反对整体的多样性，并利用建筑变化作为多样性的来源。在各种分类任务和现代体系结构搜索空间上，我们表明，所产生的合奏不仅在准确性方面超过了深层合奏，而且还不确定性校准和鲁棒性对数据集移动。我们的进一步分析和消融研究提供了由于建筑差异而引起的较高整体多样性的证据，从而导致合奏，即使平均基础学习者较弱，也可以超越深层合奏。为了培养可重复性，我们的代码可用：\ url {https://github.com/automl/nes}
Ensembles of neural networks achieve superior performance compared to stand-alone networks in terms of accuracy, uncertainty calibration and robustness to dataset shift. \emph{Deep ensembles}, a state-of-the-art method for uncertainty estimation, only ensemble random initializations of a \emph{fixed} architecture. Instead, we propose two methods for automatically constructing ensembles with \emph{varying} architectures, which implicitly trade-off individual architectures' strengths against the ensemble's diversity and exploit architectural variation as a source of diversity. On a variety of classification tasks and modern architecture search spaces, we show that the resulting ensembles outperform deep ensembles not only in terms of accuracy but also uncertainty calibration and robustness to dataset shift. Our further analysis and ablation studies provide evidence of higher ensemble diversity due to architectural variation, resulting in ensembles that can outperform deep ensembles, even when having weaker average base learners. To foster reproducibility, our code is available: \url{https://github.com/automl/nes}
