SAWA averages sample weights from multiple random initializations of DWR/SRDO-type reweighting to reduce variance and improve covariate-shift generalization.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sample Weight Averaging for Stable Prediction
SAWA averages sample weights from multiple random initializations of DWR/SRDO-type reweighting to reduce variance and improve covariate-shift generalization.