POGM combines pairwise gradient inner product maximization with a ball constraint around the ERM gradient, using a meta-learning update that avoids second-order derivatives and achieves competitive DomainBed accuracy.
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
-
Domain Generalization via Pareto Optimal Gradient Matching
POGM combines pairwise gradient inner product maximization with a ball constraint around the ERM gradient, using a meta-learning update that avoids second-order derivatives and achieves competitive DomainBed accuracy.