Supplementary Material for " Partial Optimal Transport with Applications on Positive-Unlabeled Learning '

The proof involves 3 steps: 1. we first justify the definition of p and q in the extended problem formulation, and show that T It is straighforward to see that, by doing so, we ensure that Γ remains an admissible coupling (see Figure 1 for an illustration). Figure 1: Repartition of the mass for matrices Γ and T. Each of them has a total mass of q A 5 (with a constant A > 2ξ) the GW formulation involves pairs of points. This yields the following cases: Case 1: a > 0. In that case, φ(γ) is a convex function, whose minimum on [0, 1] is reached for γ We have φ(0) = c > 0 and φ(1) = a + b + c. The minimum is then obtained for 0 if a + b > 0, and 1 otherwise. This gives the desired result.