Limits of End-to-End Learning

TL;DR

This paper critically examines the scalability and limitations of end-to-end learning, highlighting its inefficiencies and potential breakdowns when applied to complex, modular neural network architectures.

Contribution

It provides a systematic analysis of end-to-end learning's limitations, emphasizing its inefficiencies and questioning its future viability for complex systems.

Findings

End-to-end learning can become inefficient with increasing complexity.

Modular design in neural networks may not be fully exploited by end-to-end training.

Experiments show potential breakdowns of end-to-end learning in complex scenarios.

Abstract

End-to-end learning refers to training a possibly complex learning system by applying gradient-based learning to the system as a whole. End-to-end learning system is specifically designed so that all modules are differentiable. In effect, not only a central learning machine, but also all "peripheral" modules like representation learning and memory formation are covered by a holistic learning process. The power of end-to-end learning has been demonstrated on many tasks, like playing a whole array of Atari video games with a single architecture. While pushing for solutions to more challenging tasks, network architectures keep growing more and more complex. In this paper we ask the question whether and to what extent end-to-end learning is a future-proof technique in the sense of scaling to complex and diverse data processing architectures. We point out potential inefficiencies, and we argue in particular that end-to-end learning does not make optimal use of the modular design of present neural networks. Our surprisingly simple experiments demonstrate these inefficiencies, up to the complete breakdown of learning.