paper-with-me

홈 › Papers

Generalized Sliced Distances for Probability Distributions

2020-02-28 · Soheil Kolouri, Kimia Nadjahi, Umut Simsekli, Shahin Shahrampour

Probability metrics have become an indispensable part of modern statistics and machine learning, and they play a quintessential role in various applications, including statistical hypothesis testing and generative modeling. However, in a practical setting, the convergence behavior of the algorithms built upon these distances have not been well established, except for a few specific cases. In this paper, we introduce a broad family of probability metrics, coined as Generalized Sliced Probability Metrics (GSPMs), that are deeply rooted in the generalized Radon transform. We first verify that GSPMs are metrics. Then, we identify a subset of GSPMs that are equivalent to maximum mean discrepancy (MMD) with novel positive definite kernels, which come with a unique geometric interpretation. Finally, by exploiting this connection, we consider GSPM-based gradient flows for generative modeling applications and show that under mild assumptions, the gradient flow converges to the global optimum. We illustrate the utility of our approach on both real and synthetic problems.

📄 PDF Abstract BibTeX arXiv:2002.12537

Code (0)

등록된 구현이 없습니다.

Tasks

Two-sample testing

Similar Papers 제목 키워드 기반

Generalized Sliced Wasserstein Distances

2019-02-01 · NeurIPS 2019 12 · Soheil Kolouri, Kimia Nadjahi, Umut Simsekli, Roland Badeau 외

The Wasserstein distance and its variations, e.g., the sliced-Wasserstein (SW) distance, have recently drawn attention from the machine learning community. The SW distance, specifically, was shown to have similar propert…

Stereographic Spherical Sliced Wasserstein Distances

2024-02-04 · Huy Tran, Yikun Bai, Abihith Kothapalli, Ashkan Shahbazi 외

Comparing spherical probability distributions is of great interest in various fields, including geology, medical domains, computer vision, and deep representation learning. The utility of optimal transport-based distance…

Representation LearningSelf-Supervised Learning

Sliced Wasserstein Kernels for Probability Distributions

2015-11-10 · CVPR 2016 6 · Soheil Kolouri, Yang Zou, Gustavo K. Rohde

Optimal transport distances, otherwise known as Wasserstein distances, have recently drawn ample attention in computer vision and machine learning as a powerful discrepancy measure for probability distributions. The rece…

BIG-bench Machine Learning

Linear Spherical Sliced Optimal Transport: A Fast Metric for Comparing Spherical Data

2024-11-09 · Xinran Liu, Yikun Bai, Rocío Díaz Martín, Kaiwen Shi 외

Efficient comparison of spherical probability distributions becomes important in fields such as computer vision, geosciences, and medicine. Sliced optimal transport distances, such as spherical and stereographic spherica…

3D Point Cloud InterpolationComputational Efficiency

Fast Approximation of the Generalized Sliced-Wasserstein Distance

2022-10-19 · Dung Le, Huy Nguyen, Khai Nguyen, Trang Nguyen 외

Generalized sliced Wasserstein distance is a variant of sliced Wasserstein distance that exploits the power of non-linear projection through a given defining function to better capture the complex structures of the proba…