ResNet After All? Neural ODEs and Their Numerical Solution
arXiv:2007.15386
Abstract
A key appeal of the recently proposed Neural Ordinary Differential Equation (ODE) framework is that it seems to provide a continuous-time extension of discrete residual neural networks. As we show herein, though, trained Neural ODE models actually depend on the specific numerical method used during training. If the trained model is supposed to be a flow generated from an ODE, it should be possible to choose another numerical solver with equal or smaller numerical error without loss of performance. We observe that if training relies on a solver with overly coarse discretization, then testing with another solver of equal or smaller numerical error results in a sharp drop in accuracy. In such cases, the combination of vector field and numerical method cannot be interpreted as a flow generated from an ODE, which arguably poses a fatal breakdown of the Neural ODE concept. We observe, however, that there exists a critical step size beyond which the training yields a valid ODE vector field. We propose a method that monitors the behavior of the ODE solver during training to adapt its step size, aiming to ensure a valid ODE without unnecessarily increasing computational cost. We verify this adaptation algorithm on a common bench mark dataset as well as a synthetic dataset.
References in corpus (10)
- Wide Residual Networks
- ResNet with one-neuron hidden layers is a Universal Approximator
- Kernel Flows: from learning kernels from data into the abyss
- The Shattered Gradients Problem: If resnets are the answer, then what is the question?
- Multi-level Residual Networks from Dynamical Systems View
- Learning Differential Equations that are Easy to Solve
- IMEXnet: A Forward Stable Deep Neural Network
- A Mean-field Analysis of Deep ResNet and Beyond: Towards Provable Optimization Via Overparameterization From Depth
- Transport Analysis of Infinitely Deep Neural Network
- Deep learning with differential Gaussian process flows