Weak convergence of empirical Wasserstein type distances
Abstract
We estimate contrasts ∫0 1 (F-1(u)-G-1(u))du between two continuous distributions F and G on R such that the set \F=G\ is a finite union of intervals, possibly empty or R. The non-negative convex cost function is not necessarily symmetric and the sample may come from any joint distribution H on R2 with marginals F and G having light enough tails with respect to . The rates of weak convergence and the limiting distributions are derived in a wide class of situations including the classical Wasserstein distances W1 and W2. The new phenomenon we describe in the case F=G involves the behavior of near 0, which we assume to be regularly varying with index ranging from 1 to 2 and to satisfy a key relation with the behavior of near ∞ through the common tails. Rates are then also regularly varying with powers ranging from 1/2 to 1 also affecting the limiting distribution, in addition to H.
Turn this paper into a lesson
ArcXiv compiles a structured reading guide from this paper's metadata: plain-English importance, contributions, prerequisite concepts, which sections to read first, flashcards, and a quiz. Grounded in the abstract, never invented.