AI RESEARCH
When Do Early-Exit Networks Generalize? A PAC-Bayesian Theory of Adaptive Depth
arXiv CS.AI
•
ArXi:2604.15764v1 Announce Type: cross Early-exit neural networks enable adaptive computation by allowing confident predictions to exit at intermediate layers, achieving 2-8$\times$ inference speedup. Despite widespread deployment, their generalization properties lack theoretical understanding -- a gap explicitly identified in recent surveys. This paper establishes a unified PAC-Bayesian framework for adaptive-depth networks.