the.ai

Inference / Adaptive

verified

Early Exit

Stop partway up the stack when the answer is already clear. Attach a small classifier to intermediate layers, and if one of them is confident enough, return from there rather than running the remaining layers. Easy inputs leave early; hard ones go all the way.

Viz primitive · threshold-sweepseparation = 1.8 · threshold = 0.9 · base-rate = 0.4
let throughcutflagged

436 of 1000 flagged. 75% of them were right and 107 were false alarms; 82% of what should have been caught was, leaving 71 missed.

Inputs an early exit would answer correctly against ones it would get wrong, by the exit head's confidence. Drag the threshold up to watch the wrong exits fall away and the saving fall with them — one dial sets both, which is why a speedup alone says nothing.

0.9

Reviewed by opendroid · 2026-08-18

  • arXiv:2004.12993 — DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
  • arXiv:1709.01686 — BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks