The authors define a total pair concept shift on the optimal transport plan between source and target covariates, yielding a Lipschitz-based target error bound that handles stochastic labels, general losses, and mismatched supports.
Convergence of entropic schemes for optimal transport and gradient flows
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
-
General and Estimable Learning Bound Unifying Covariate and Concept Shifts
The authors define a total pair concept shift on the optimal transport plan between source and target covariates, yielding a Lipschitz-based target error bound that handles stochastic labels, general losses, and mismatched supports.