发表机构
Université de Technologie de Compiègne; Japan Advanced Institute of Science and Technology（贡比涅技术大学; 日本先端科学技术大学院大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出使用紧致集成（如贝叶斯神经网络和蒙特卡洛丢弃卷积神经网络）生成概率预测，并定义代表性分布以优化统计距离，从而高效计算集值贝叶斯最优预测，解决深度集成中的训练存储负担和单值预测不鲁棒问题。
AI 中文摘要
本文解决了深度集成学习中可见的挑战，其中深度神经网络作为集成成员：训练和存储负担，以及针对多种效用（可能涉及奖励敏感性）的谨慎（集值）预测的鲁棒性。为了减轻训练和存储负担，我们提出采用紧致集成，如贝叶斯神经网络和具有蒙特卡洛丢弃预测选项的卷积神经网络，以产生概率预测。对于每个查询实例，这些概率预测随后用于定义一个代表性分布，该分布优化某种统计距离。然后使用该代表性分布来定义任何效用的贝叶斯最优预测（BOP）。为了解决单值预测可能的不鲁棒性，我们提出了一族满足某些期望性质且其集值BOP可以高效计算的集效用。随后给出实证证据以说明所提出的集成学习框架的潜在（不利）优势。
英文摘要
This paper tackles visible challenges in deep ensemble learning, where deep neural networks serve as ensemble members: training and storage burdens, and robustness of cautious (set-valued) predictions targeting multiple utilities, which may involve reward-sensitivity. To mitigate the training and storage burdens, we propose to employ compact ensembles, such as Bayesian Neural Networks and Convolutional Neural Networks with the Monte-Carlo dropout prediction option, to produce probabilistic predictions. For each query instance, these probabilistic predictions are then used to define a representative distribution optimizing some statistical distance. The representative distribution is then employed to define the Bayes-optimal prediction (BOP) of any utility. To address the potential unrobustness of singleton prediction making, we propose a family of set-utilities satisfying some desirable properties and whose set-valued BOPs can be found efficiently. Empirical evidence is then given to illustrate the potential (dis)advantages of the proposed ensemble learning framework.
