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}
翻译:与独立网络相比,神经网络组合在精确度、不确定性校准度和对数据集转换的稳健度方面实现优异性。 \ emph{ deep ensembles}, 这是一种最先进的不确定性估计方法, 只能混合随机随机初始化 。 相反, 我们提出了两种方法, 用来自动构建与 emph{ fixed} 建筑相匹配的组合, 这种方法隐含了个人结构在对共性多样性的优势进行交易, 并且利用建筑变异作为多样性的来源。 在各种分类任务和现代建筑搜索空间方面, 我们显示, 由此产生的组合不仅在准确性方面, 而且还在不确定性校准和数据置置变的稳性方面, 超越了深度的组合。 我们的进一步分析和校正研究表明, 建筑变异性会带来更高的共性多样性, 导致可以超越深层组合的组合, 甚至当有较弱的普通的学习者时, 。 为促进再生能力, 我们的代码是: auvibnomrgnes/ {comms。