Reframing decision-focused learning as cost-sensitive multi-output regression with cost-insensitive normalization, decision-aware asymmetric penalization, and instance-based costs enables scalable training with comparable task quality but far fewer optimization solves.
Differentiating through integer lin- ear programs with quadratic regularization and Davis-Yin splitting.Trans
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Scalable Decision-Focused Learning through Cost-Sensitive Regression
Reframing decision-focused learning as cost-sensitive multi-output regression with cost-insensitive normalization, decision-aware asymmetric penalization, and instance-based costs enables scalable training with comparable task quality but far fewer optimization solves.