DRCS derives an upper bound on worst-case validation error under covariate shift and greedily chooses a coreset that minimizes this bound.
As a method to solve the constrained maximization ofDGi inW, we apply method of Lagrange multiplier
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Distributionally Robust Coreset Selection under Covariate Shift
DRCS derives an upper bound on worst-case validation error under covariate shift and greedily chooses a coreset that minimizes this bound.