委托-代理协作学习问题的决策论模型
A decision-theoretic model for a principal-agent collaborative learning problem
AI总结:
本文提出一个委托-代理协作学习框架的决策论模型,委托人根据代理在独立测试集上的表现动态确定聚合系数,引导代理通过带类平均场交互项的Langevin动力学达成最优参数共识,在无需了解彼此数据分布的情况下提升稳定性和泛化性。
摘要:
在本技术笔记中,我们考虑一个具有委托-代理设定的协作学习框架,其中委托人在每个时间步根据一组$K$个代理的当前参数估计在与一个独立测试数据集(不属于代理的训练模型数据集)关联中的有效表现,确定一组适当的聚合系数。而作为团队共同行动的代理,随后使用带有类平均场交互项的Langevin动力学离散时间版本更新其参数估计,但受各自不同的训练模型数据集引导。在此,我们提出一个决策论框架,明确描述委托人如何逐步确定一组非负且和为一的聚合系数,供代理在其类平均场交互项中使用,最终引导他们达成共识的最优参数估计。有趣的是,由于代理间固有的反馈和合作行为,所提框架在稳定性和泛化性方面具有一些优势,尽管委托人和代理都不必了解样本分布或彼此数据集的质量。
英文摘要:
In this technical note, we consider a collaborative learning framework with principal-agent setting, in which the principal at each time-step determines a set of appropriate aggregation coefficients based on how the current parameter estimates from a group of $K$ agents effectively performed in connection with a separate test dataset, which is not part of the agents' training model datasets. Whereas, the agents, who act together as a team, then update their parameter estimates using a discrete-time version of Langevin dynamics with mean-field-like interaction term, but guided by their respective different training model datasets. Here, we propose a decision-theoretic framework that explicitly describes how the principal progressively determines a set of nonnegative and sum to one aggregation coefficients used by the agents in their mean-field-like interaction term, that eventually leading them to reach a consensus optimal parameter estimate. Interestingly, due to the inherent feedbacks and cooperative behavior among the agents, the proposed framework offers some advantages in terms of stability and generalization, despite that both the principal and the agents do not necessarily need to have any knowledge of the sample distributions or the quality of each others' datasets.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。