On the Sample Complexity of End-to-end Training vs. Semantic Abstraction Training
This addresses the problem of high sample complexity in end-to-end training for safety-critical applications like autonomous driving, highlighting a potential efficiency advantage of modular methods.
The paper compares end-to-end training with modular semantic abstraction training, showing that in high-accuracy regimes like autonomous driving, end-to-end training can require exponentially more training examples than the semantic abstraction approach.
We compare the end-to-end training approach to a modular approach in which a system is decomposed into semantically meaningful components. We focus on the sample complexity aspect, in the regime where an extremely high accuracy is necessary, as is the case in autonomous driving applications. We demonstrate cases in which the number of training examples required by the end-to-end approach is exponentially larger than the number of examples required by the semantic abstraction approach.