Kaheon Kim — accepted AI-conference papers

2026

Sobolev Gradient Ascent for Optimal Transport: Barycenter Optimization and Convergence Analysis

Kaheon Kim, Bohan Zhou, Changbo Zhu, Xiaohui Chen

ICLR 2026poster

This paper introduces a new constraint-free concave dual formulation for the Wasserstein barycenter. Tailoring the vanilla dual gradient ascent algorithm to the Sobolev geometry, we derive a scalable Sobolev gradient ascent (SGA) algorithm to compute the barycenter for input distributions supported…

Cited by 0 Source ↗Scholar ↗

2025

Optimal Transport Barycenter via Nonconvex-Concave Minimax Optimization

Kaheon Kim, Rentian Yao, Changbo Zhu, Xiaohui Chen

ICML 2025poster

The optimal transport barycenter (a.k.a. Wasserstein barycenter) is a fundamental notion of averaging that extends from the Euclidean space to the Wasserstein space of probability distributions. Computation of the *unregularized* barycenter for discretized probability distributions on point clouds i…

Cited by 1 Source ↗PDF ↗Scholar ↗