Mar 30, 2022 · In this paper, we do away with surrogates altogether and instead learn loss functions that capture task-specific information.

Optimizing directly for the quality of decisions induced by the predictive model in this end-to-end manner yields a loss function we call the decision loss.

Code for "Decision-Focused Learning without Differentiable Optimization: Learning Locally Optimized Decision Losses" - sanketkshah/LODLs.

Decision-Focused Learning without. Decision-Making: Learning Locally. Optimized Decision Losses. Sanket Shah. 1. Page 2. Motivation: ML-based Decision Making.

We show how decision-focused learning can improve the fairness-accuracy tradeoff in algorithmic decision-making using a case study on a real-world domain.

Decision-Focused Learning (DFL) is a paradigm for tailoring a predictive model to a downstream optimization task that uses its predictions in order to ...

Missing: Making: | Show results with:Making:

Decision-Focused Learning (DFL) is an emerging learning paradigm that tackles the task of training a machine learning (ML) model to predict missing parameters ...

Mar 30, 2022 · This paper is the first approach that entirely replaces the optimization component of decision-focused learning with a loss that is automatically learned.

Learning convex & smooth loss functions for decision-focused ... Decision-Focused Learning without Decision-Making: Learning Locally Optimized Decision.