Imbedding Deep Neural NetworksDownload PDF

29 Sept 2021, 00:31 (modified: 15 Feb 2022, 10:00)ICLR 2022 SpotlightReaders: Everyone
Keywords: Neural ODEs, Optimal Control, Deep Neural Networks, Invariant Imbedding
Abstract: Continuous-depth neural networks, such as Neural ODEs, have refashioned the understanding of residual neural networks in terms of non-linear vector-valued optimal control problems. The common solution is to use the adjoint sensitivity method to replicate a forward-backward pass optimisation problem. We propose a new approach which explicates the network's `depth' as a fundamental variable, thus reducing the problem to a system of forward-facing initial value problems. This new method is based on the principal of `Invariant Imbedding' for which we prove a general solution, applicable to all non-linear, vector-valued optimal control problems with both running and terminal loss. Our new architectures provide a tangible tool for inspecting the theoretical--and to a great extent unexplained--properties of network depth. They also constitute a resource of discrete implementations of Neural ODEs comparable to classes of imbedded residual neural networks. Through a series of experiments, we show the competitive performance of the proposed architectures for supervised learning and time series prediction.
One-sentence Summary: Invariant imbedding solution for (Bolza) optimal control problem derived and proved to yield new architectures of imbedded deep neural networks.
Supplementary Material: zip
16 Replies