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 2202.01889cs.LGcs.AIstat.ML
收藏

基于上下文信息动力学模型的新物理系统推广

Generalizing to New Physical Systems via Context-Informed Dynamics Model

Sorbonne University(索邦大学);Criteo AI Lab(Criteo人工智能实验室);Université de Rouen(鲁昂大学)

Matthieu Kirchmeyer, Yuan Yin, Jérémie Donà, Nicolas Baskiotis, Alain Rakotomamonjy, Patrick Gallinari

摘要:

数据驱动的物理系统建模方法无法推广到与学习领域共享相同的一般动态,但对应于不同的物理环境的看不见的系统。我们提出了一个新的框架,这个关键问题,上下文知情的动态适应(CoDA),它考虑到系统之间的分布转移,快速,有效地适应新的动态。CoDA利用多个环境,每个环境与不同的动态相关联,并学习根据特定于每个环境的上下文参数来调节动态模型。通过超网络进行调节,从观察到的数据与上下文向量共同学习。所提出的公式约束搜索假设空间,以促进快速适应和更好的泛化跨环境。我们从理论上激励我们的方法,并显示一组非线性动力学,代表各种应用领域的最先进的推广结果。我们还表明,在这些系统中,新的系统参数可以推断出上下文向量与最小的监督。代码可在https://github.com/yuan-yin/CoDA上获得。

英文摘要:

Data-driven approaches to modeling physical systems fail to generalize to unseen systems that share the same general dynamics with the learning domain, but correspond to different physical contexts. We propose a new framework for this key problem, context-informed dynamics adaptation (CoDA), which takes into account the distributional shift across systems for fast and efficient adaptation to new dynamics. CoDA leverages multiple environments, each associated to a different dynamic, and learns to condition the dynamics model on contextual parameters, specific to each environment. The conditioning is performed via a hypernetwork, learned jointly with a context vector from observed data. The proposed formulation constrains the search hypothesis space to foster fast adaptation and better generalization across environments. We theoretically motivate our approach and show state-of-the-art generalization results on a set of nonlinear dynamics, representative of a variety of application domains. We also show, on these systems, that new system parameters can be inferred from context vectors with minimal supervision. Code is available at https://github.com/yuan-yin/CoDA .

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。

↑