End-to-End Optimization and Learning for Multiagent Ensembles
End-to-End Optimization and Learning for Multiagent Ensembles
复制标题
DOI：
10.48550/arxiv.2211.00251
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
James Kotary;Vincenzo Di Vito;Ferdinando Fioretto
中科院分区：
文献类型：
--
作者：
James Kotary;Vincenzo Di Vito;Ferdinando Fioretto
多基金会合奏学习是一类重要的算法类别，旨在通过结合各个代理的预测来创建准确，健壮的机器学习模型。这些模型设计的主要挑战是创建有效的规则，以结合任何特定输入样本的个人预测。本文解决了这一挑战，并提出了约束优化和学习的独特集成，以得出专业的共识规则，以从经过预定的合奏中构成准确的预测。所得的策略称为端到端多构成集合学习E2E-MEL，学会了选择适当的预测因子以合并特定输入样本。本文显示了如何将集成学习任务推导到一个可区分的选择程序中，该程序是在集合学习模型中端到端训练的。根据标准基准测试的结果表明，在各种设置中，E2E-MEL在大大优于常规共识规则的能力上。
Multiagent ensemble learning is an important class of algorithms aimed at creating accurate and robust machine learning models by combining predictions from individual agents. A key challenge for the design of these models is to create effective rules to combine individual predictions for any particular input sample. This paper addresses this challenge and proposes a unique integration of constrained optimization and learning to derive specialized consensus rules to compose accurate predictions from a pretrained ensemble. The resulting strategy, called end-to-end Multiagent ensemble Learning e2e-MEL , learns to select appropriate predictors to combine for a particular input sample. The paper shows how to derive the ensemble learning task into a differentiable selection program which is trained end-to-end within the ensemble learning model. Results over standard benchmarks demonstrate the ability of e2e-MEL to substantially outperform conventional consensus rules in a variety of settings.