4 papers
Entropic vector quantile regression: Duality and Gaussian case
Kengo Kato, Boyu Wang
Vector quantile regression (VQR) is an optimal transport (OT) problem subject to a mean-independence constraint that extends classical linear quantile regression to vector response…
Deviation Inequalities for Rényi Divergence Estimators via Variational Expression
Sreejith Sreekumar, Kengo Kato
Rényi divergences play a pivotal role in information theory, statistics, and machine learning. While several estimators of these divergences have been proposed in the literature w…
Convergence of empirical Gromov-Wasserstein distance
Kengo Kato, Boyu Wang
We study rates of convergence for estimation of the Gromov-Wasserstein (GW) distance. For two marginals supported on compact subsets of and , respectively, wit…
Large deviations for dynamical Schrödinger problems
Kengo Kato
We establish large deviations for dynamical Schrödinger problems driven by perturbed Brownian motions when the noise parameter tends to zero. Our results show that Schrödinger br…