REVIEW 2 cited by
Self-Distillation Amplifies Regularization in Hilbert Space
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Knowledge distillation introduced in the deep learning context is a method to transfer knowledge from one architecture to another. In particular, when the architectures are identical, this is called self-distillation. The idea is to feed in predictions of the trained model as new target values for retraining (and iterate this loop possibly a few times). It has been empirically observed that the self-distilled model often achieves higher accuracy on held out data. Why this happens, however, has been a mystery: the self-distillation dynamics does not receive any new information about the task and solely evolves by looping over training. To the best of our knowledge, there is no rigorous understanding of this phenomenon. This work provides the first theoretical analysis of self-distillation. We focus on fitting a nonlinear function to training data, where the model space is Hilbert space and fitting is subject to $\ell_2$ regularization in this function space. We show that self-distillation iterations modify regularization by progressively limiting the number of basis functions that can be used to represent the solution. This implies (as we also verify empirically) that while a few rounds of self-distillation may reduce over-fitting, further rounds may lead to under-fitting and thus worse performance.
Forward citations
Cited by 2 Pith papers
-
Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling
Distilled pretraining improves test-time scaling via generation diversity but impairs induction-head-based in-context learning, with the trade-off explained by a bigram model analysis.
-
Optimal Self-Distillation for Rectified Flow via Linear Probing
For linear rectified flow with ridge regression on fixed interpolants, optimally mixed self-distillation strictly improves velocity risk whenever the teacher is off the ridge stationary point, with a closed-form mixin...
Discussion (0). Continue with ORCID to comment.