A Fisher information penalty added to the loss during batchwise training is claimed to correct covariate shift and improve accuracy, but the supporting derivation and experiments are incomplete.
Rethinking importance weighting for deep learning under distribution shift
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
-
Causal Covariate Shift Correction using Fisher information penalty
A Fisher information penalty added to the loss during batchwise training is claimed to correct covariate shift and improve accuracy, but the supporting derivation and experiments are incomplete.