How Deep Do We Need: Accelerating Training and Inference of Neural ODEs via Control Perspective

Keyan Miao; Konstantinos Gatsis

2024 ICML ICML 2024

How Deep Do We Need: Accelerating Training and Inference of Neural ODEs via Control Perspective

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Robotics

Authors

Keyan Miao, Konstantinos Gatsis

Topics

Machine Learning > Optimization & Theory > Optimization Deep Learning > Architectures > Neural Networks Robotics > Systems > Control Theory

Keywords

pretraining optimal control neural ode lyapunov method forward direction terminal time

Download PDF