Towards an Optimal Control Perspective of ResNet Training

No Thumbnail Available

Date

2025

Journal Title

Journal ISSN

Volume Title

Publisher

Alternative Title(s)

Abstract

We propose a training formulation for ResNets reflecting an optimal control problem that is applicable for standard architectures and general loss functions. We suggest bridging both worlds via penalizing intermediate outputs of hidden states corresponding to stage cost terms in optimal control. For standard ResNets, we obtain intermediate outputs by propagating the state through the subsequent skip connections and the output layer. We demonstrate that our training dynamic biases the weights of the unnecessary deeper residual layers to vanish. This indicates the potential for a theory-grounded layer pruning strategy.

Description

Table of contents

Keywords

ResNets, optimal control, regularization, network depth

Subjects based on RSWK

Citation