Feasible Flow Matching for Graph Reconstruction via Within-Sampling Primal-Dual Guidance
Constrained Primal-Dual PIFM (CPD-PIFM), which augments the sampler with Lagrange multipliers that evolve along each trajectory, raises feasibility by 11-26 percentage points and remains competitive with fixed guidance without selecting a separate multiplier for each constraint.
Hao-Ming Chen, Nicolas Zilberstein, Santiago Paternain et al.
· 0 citations