标题： 元学习中的分布鲁棒最小化用于系统识别 显示英文标题

标题： Distributionally robust minimization in meta-learning for system identification

摘要： 元学习旨在学习如何解决问题，因此它允许估计可以快速适应新场景的模型。 本工作探讨了在元学习中用于系统识别的分布鲁棒最小化。 标准的元学习方法优化期望损失，忽视了任务的变异性。 我们采用了一种替代方法，采用分布鲁棒优化范式，优先考虑高损失任务，从而提高最坏情况下的性能。 在一类合成动态系统上训练的元模型上进行评估，并在分布内和分布外设置下进行测试，所提出的方法有助于减少安全关键应用中的故障。 显示英文摘要

摘要： Meta learning aims at learning how to solve tasks, and thus it allows to estimate models that can be quickly adapted to new scenarios. This work explores distributionally robust minimization in meta learning for system identification. Standard meta learning approaches optimize the expected loss, overlooking task variability. We use an alternative approach, adopting a distributionally robust optimization paradigm that prioritizes high-loss tasks, enhancing performance in worst-case scenarios. Evaluated on a meta model trained on a class of synthetic dynamical systems and tested in both in-distribution and out-of-distribution settings, the proposed approach allows to reduce failures in safety-critical applications.