STEER: simple temporal regularization for neural ODEs

Conference item

Training Neural Ordinary Differential Equations (ODEs) is often computationally expensive. Indeed, computing the forward pass of such models involves solving an ODE which can become arbitrarily complex during training. Recent works have shown that regularizing the dynamics of the ODE can partially alleviate this. In this paper we propose a new regularization technique: randomly sampling the end time of the ODE during training. The proposed regularization is simple to implement, has negligible overhead and is effective across a wide variety of tasks. Further, the technique is orthogonal to several other methods proposed to regularize the dynamics of ODEs and as such can be used in conjunction with them. We show through experiments on normalizing flows, time series models and image recognition that the proposed regularization can significantly decrease training time and even improve performance over baseline models.

Authors: Ghosh, A; Behl, HS; Dupont, E; Torr, PHS; Namboodiri, V

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Neural Information Processing Systems Foundation, Inc.
• Host title: Advances in Neural Information Processing Systems 33 (NeurIPS 2020)
• Pages: 1-13
• Publication date: 2020-12-11
• Acceptance date: 2020-09-25
• Event title: 34th Conference on Neural Information Processing Systems (NeurIPS)
• Event location: Virtual
• Event website: https://neurips.cc/
• Event start date: 2020-12-06
• Event end date: 2020-12-12
• Language: English
• Keywords: FFR