The paper claims an optimal weighting parameter and higher-order asymptotic corrections for batch-normalization test-time adaptation, but the central derivations contain sign errors, ad hoc terms, and an invalid consistency assumption.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Higher-Order Asymptotics of Test-Time Adaptation for Batch Normalization Statistics
The paper claims an optimal weighting parameter and higher-order asymptotic corrections for batch-normalization test-time adaptation, but the central derivations contain sign errors, ad hoc terms, and an invalid consistency assumption.