paper-with-me

홈 › Papers

Non-geodesically-convex optimization in the Wasserstein space

2024-06-01 · Hoang Phuc Hau Luu, Hanlin Yu, Bernardo Williams, Petrus Mikkola, Marcelo Hartmann, Kai Puolamäki, Arto Klami

We study a class of optimization problems in the Wasserstein space (the space of probability measures) where the objective function is nonconvex along generalized geodesics. Specifically, the objective exhibits some difference-of-convex structure along these geodesics. The setting also encompasses sampling problems where the logarithm of the target distribution is difference-of-convex. We derive multiple convergence insights for a novel semi Forward-Backward Euler scheme under several nonconvex (and possibly nonsmooth) regimes. Notably, the semi Forward-Backward Euler is just a slight modification of the Forward-Backward Euler whose convergence is -- to our knowledge -- still unknown in our very general non-geodesically-convex setting.

📄 PDF Abstract BibTeX arXiv:2406.00502

Code (1)

mcs-hub/ow24 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Accelerated Multiple Wasserstein Gradient Flows for Multi-objective Distributional Optimization

2026-01-27 · Dai Hai Nguyen, Duc Dung Nguyen, Atsuyoshi Nakamura, Hiroshi Mamitsuka arxiv

We study multi-objective optimization over probability distributions in Wasserstein space. Recently, Nguyen et al. (2025) introduced Multiple Wasserstein Gradient Descent (MWGraD) algorithm, which exploits the geometric …

Nonconvex Matrix Factorization is Geodesically Convex: Global Landscape Analysis for Fixed-rank Matrix Optimization From a Riemannian Perspective

2022-09-29 · Yuetian Luo, Nicolas Garcia Trillos

We study a general matrix optimization problem with a fixed-rank positive semidefinite (PSD) constraint. We perform the Burer-Monteiro factorization and consider a particular Riemannian quotient geometry in a search spac…

Accelerated First-order Methods for Geodesically Convex Optimization on Riemannian Manifolds

2017-12-01 · NeurIPS 2017 12 · Yuanyuan Liu, Fanhua Shang, James Cheng, Hong Cheng 외

In this paper, we propose an accelerated first-order method for geodesically convex optimization, which is the generalization of the standard Nesterov's accelerated method from Euclidean space to nonlinear Riemannian spa…

Random Coordinate Descent on the Wasserstein Space of Probability Measures

2026-04-02 · Yewei Xu, Qin Li arxiv

Optimization over the space of probability measures endowed with the Wasserstein-2 geometry is central to modern machine learning and mean-field modeling. However, traditional methods relying on full Wasserstein gradient…

The Wasserstein Proximal Gradient Algorithm

2020-02-07 · NeurIPS 2020 12 · Adil Salim, Anna Korba, Giulia Luise

Wasserstein gradient flows are continuous time dynamics that define curves of steepest descent to minimize an objective function over the space of probability measures (i.e., the Wasserstein space). This objective is typ…