paper-with-me

Papers

A Fast Proximal Point Method for Computing Exact Wasserstein Distance

2018-02-12 · Yujia Xie, Xiangfeng Wang, Ruijia Wang, Hongyuan Zha

Wasserstein distance plays increasingly important roles in machine learning, stochastic programming and image processing. Major efforts have been under way to address its high computational complexity, some leading to approximate or regularized variations such as Sinkhorn distance. However, as we will demonstrate, regularized variations with large regularization parameter will degradate the performance in several important machine learning applications, and small regularization parameter will fail due to numerical stability issues with existing algorithms. We address this challenge by developing an Inexact Proximal point method for exact Optimal Transport problem (IPOT) with the proximal operator approximately evaluated at each iteration using projections to the probability simplex. The algorithm (a) converges to exact Wasserstein distance with theoretical guarantee and robust regularization parameter selection, (b) alleviates numerical stability issue, (c) has similar computational complexity to Sinkhorn, and (d) avoids the shrinking problem when apply to generative models. Furthermore, a new algorithm is proposed based on IPOT to obtain sharper Wasserstein barycenter.

📄 PDF Abstract BibTeX arXiv:1802.04307

Code (1)

xieyujia/IPOT tf

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Convergence Analysis of the Wasserstein Proximal Algorithm beyond Geodesic Convexity

2025-01-25 · Shuailong Zhu, Xiaohui Chen

The proximal algorithm is a powerful tool to minimize nonlinear and nonsmooth functionals in a general metric space. Motivated by the recent progress in studying the training dynamics of the noisy gradient descent algori…

ITSPACE: Monotone Gaussian Optimal Transport Updates

2026-06-29 · Woojoo Na, Jennifer Dy arxiv

Covariance matrices serve as compact descriptors of feature distributions in many machine-learning pipelines, including domain adaptation and Gaussian embeddings. Under a centered Gaussian approximation, the unregularize…

Domain Adaptation

Wasserstein Proximal Policy Gradient

2026-03-03 · Zhaoyu Zhu, Shuhan Zhang, Rui Gao, Shuang Li arxiv

We study policy gradient methods for continuous-action, entropy-regularized reinforcement learning through the lens of Wasserstein geometry. Starting from a Wasserstein proximal update, we derive Wasserstein Proximal Pol…

Reinforcement Learning

Riemannian Proximal Sampler for High-accuracy Sampling on Manifolds

2025-02-11 · Yunrui Guan, Krishnakumar Balasubramanian, Shiqian Ma

We introduce the Riemannian Proximal Sampler, a method for sampling from densities defined on Riemannian manifolds. The performance of this sampler critically depends on two key oracles: the Manifold Brownian Increments …

Complexity of Block Coordinate Descent with Proximal Regularization and Applications to Wasserstein CP-dictionary Learning

2023-06-04 · Dohyun Kwon, Hanbaek Lyu

We consider the block coordinate descent methods of Gauss-Seidel type with proximal regularization (BCD-PR), which is a classical method of minimizing general nonconvex objectives under constraints that has a wide range …

Dictionary Learning