Quantitative Stability and Sample Complexity for Regularized Gromov-Wasserstein Distance
Pengtao Li, Xiaohui Chen
Abstract
The Gromov-Wasserstein (GW) distance provides a principled framework for comparing two probability distributions supported on different metric spaces by matching their individual intrinsic geometric structures. In practice, the GW distance is estimated from finite samples and often incorporates regularization for statistical and computational tractability. This motivates a quantitative understanding of the stability and estimation error of regularized GW distances. In this work, we study a general family of divergence regularized GW distances, including entropy and Tsallis regularizations over the full range of powers, from a nonasymptotic perspective. Specifically, we establish Lipschitz continuity of the value of regularized GW and Hölder continuity of its optimal coupling under Wasserstein perturbations of the input probability measures. Moreover, we derive the parametric rate of convergence for the empirical regularized (2,2)-GW distance on compactly supported Euclidean spaces.
Create a lesson
Related papers
Robust Nonparametric Methods for α-Mixing Sequences via Median-of-Means
Attila Lovas, Marcell Tukora
Separating Statistical Inference from Experimental Runtime: An Architecture for Sequential Scientific Analysis
Alexander Stepanov, Andrej Novikov
Sub-Gaussian Confidence Intervals for Heavy-Tailed Data: Characterizing the Limits of Inference
Ilyes Hammouda, Stanislav Minsker, Mohamed Ndaoud
Adaptive Robust Confidence Sets in High Dimensions
Ilias Diakonikolas, Chao Gao, Daniel M. Kane et al.
Synergistic Learning in Domain Adaptation with a Known Link: A Minimax Understanding
Pengcheng Xiang, Ling Zhou, Yuhong Yang
Rank-based Model Average Estimator for Average Treatment Effects
Jing Lv, Jialiang Li