The paper claims transformer models, modeled as Gevrey-smooth maps, have sub-exponential MSE growth under Wasserstein-measured distribution shift, but the proof uses a false lemma and the validation fits its constants to the data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A Theoretical Framework for OOD Robustness in Transformers using Gevrey Classes
The paper claims transformer models, modeled as Gevrey-smooth maps, have sub-exponential MSE growth under Wasserstein-measured distribution shift, but the proof uses a false lemma and the validation fits its constants to the data.