AI RESEARCH
Decision-Focused Federated Learning Under Heterogeneous Objectives and Constraints
arXiv CS.LG
•
ArXi:2604.20031v1 Announce Type: cross We consider what we refer to as {Decision-Focused Federated Learning (DFFL)} framework, i.e., a predict-then-optimize approach employed by a collection of agents, where each agent's predictive model is an input to a downstream linear optimization problem, and no direct exchange of raw data is allowed. Importantly, clients can differ both in objective functions and in feasibility constraints. We build on the well-known SPO+ approach and develop heterogeneity bounds for the SPO+ surrogate loss in this case.