arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2112.05729cs.LG
收藏

复杂平衡系统中的软干预学习

Learning soft interventions in complex equilibrium systems

Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)

Michel Besserve, Bernhard Schölkopf

摘要:

复杂系统通常包含反馈回路,可以描述为循环因果模型。干预这样的系统可能会导致违反直觉的效果,这不能直接从图形结构中推断出来。在建立了基于李群的可微软干预框架之后,我们利用现代自动微分技术及其在隐函数中的应用,对循环因果模型中的干预进行了优化。我们通过调查向可持续经济过渡的情景来说明这一框架的使用。

英文摘要:

Complex systems often contain feedback loops that can be described as cyclic causal models. Intervening in such systems may lead to counterintuitive effects, which cannot be inferred directly from the graph structure. After establishing a framework for differentiable soft interventions based on Lie groups, we take advantage of modern automatic differentiation techniques and their application to implicit functions in order to optimize interventions in cyclic causal models. We illustrate the use of this framework by investigating scenarios of transition to sustainable economies.

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。

↑