Using a pretrained reference model inside a distributionally robust risk objective can improve generalization bounds and yields a CLIP variant that matches baseline performance with half the data.
Net2net: Accelerating learning via knowledge transfer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Model Steering: Learning with a Reference Model Improves Generalization Bounds and Scaling Laws
Using a pretrained reference model inside a distributionally robust risk objective can improve generalization bounds and yields a CLIP variant that matches baseline performance with half the data.