A conventional approach to train neural ordinary differential equations (ODEs) is to fix an ODE solver and then learn the neural network's weights to optimize a target loss function. However, such an approach is tailored for a specific discretization method and its properties, which may not be optimal for the selected application and yield the overfitting to the given solver. In our paper, we investigate how the variability in solvers' space can improve neural ODEs performance. We consider a family of Runge-Kutta methods that are parameterized by no more than two scalar variables. Based on the solvers' properties, we propose an approach to decrease neural ODEs overfitting to the pre-defined solver, along with a criterion to evaluate such behaviour. Moreover, we show that the right choice of solver parameterization can significantly affect neural ODEs models in terms of robustness to adversarial attacks. Recently it was shown that neural ODEs demonstrate superiority over conventional CNNs in terms of robustness. Our work demonstrates that the model robustness can be further improved by optimizing solver choice for a given task. The source code to reproduce our experiments is available at https://github.com/juliagusak/neural-ode-metasolver.
翻译:培养神经普通差异方程式(ODEs)的常规方法,是修补一个 ODE 求解器,然后学习神经网络的重量,以优化目标损失功能。然而,这种方法是针对特定离散方法及其特性而设计的,可能不适合选定的应用程序,并且使给定求解器的过度适应。在我们的论文中,我们调查了解决问题者空间的变异性如何能改善神经求解器的性能。我们考虑了龙格-库塔方法的组合,这些方法的参数不超过两个星座变量。根据解答器的特性,我们建议了一种方法来减少超出预定的求解器的神经求解码及其特性,同时提出了评估这种行为的标准。此外,我们表明,从强势到对抗性攻击,求解码参数的正确选择会大大影响神经求解码模型的模型。最近我们的工作表明,神经求解码在强性方面比常规CNN的强。我们的工作表明,通过优化求解器选择某项任务,可以进一步改进模型的坚固性。