中文
相关论文

相关论文: An Empirical Study of Self-supervised Learning wit…

200 篇论文

Wasserstein distance, which measures the discrepancy between distributions, shows efficacy in various types of natural language processing (NLP) and computer vision (CV) applications. One of the challenges in estimating Wasserstein distance…

机器学习 · 统计学 2022-06-27 Makoto Yamada , Yuki Takezawa , Ryoma Sato , Han Bao , Zornitsa Kozareva , Sujith Ravi

To measure the similarity of documents, the Wasserstein distance is a powerful tool, but it requires a high computational cost. Recently, for fast computation of the Wasserstein distance, methods for approximating the Wasserstein distance…

机器学习 · 计算机科学 2021-07-26 Yuki Takezawa , Ryoma Sato , Makoto Yamada

The performance of unsupervised methods such as clustering depends on the choice of distance metric between features, or ground metric. Commonly, ground metrics are decided with heuristics or learned via supervised algorithms. However,…

机器学习 · 计算机科学 2025-01-13 Kira M. Düsterwald , Samo Hromadka , Makoto Yamada

Sliced Wasserstein (SW) distances offer an efficient method for comparing high-dimensional probability measures by projecting them onto multiple 1-dimensional probability distributions. However, identifying informative slicing directions…

机器学习 · 计算机科学 2025-06-04 Navid NaderiAlizadeh , Darian Salehi , Xinran Liu , Soheil Kolouri

Finding meaningful distances between high-dimensional data samples is an important scientific task. To this end, we propose a new tree-Wasserstein distance (TWD) for high-dimensional data with two key aspects. First, our TWD is specifically…

机器学习 · 计算机科学 2025-02-25 Ya-Wei Eileen Lin , Ronald R. Coifman , Gal Mishne , Ronen Talmon

Comparing probability distributions is at the crux of many machine learning algorithms. Maximum Mean Discrepancies (MMD) and Wasserstein distances are two classes of distances between probability distributions that have attracted abundant…

机器学习 · 统计学 2023-06-01 Titouan Vayer , Rémi Gribonval

The Sliced-Wasserstein distance (SW) is being increasingly used in machine learning applications as an alternative to the Wasserstein distance and offers significant computational and statistical benefits. Since it is defined as an…

机器学习 · 统计学 2022-01-05 Kimia Nadjahi , Alain Durmus , Pierre E. Jacob , Roland Badeau , Umut Şimşekli

Optimal Transport has sparked vivid interest in recent years, in particular thanks to the Wasserstein distance, which provides a geometrically sensible and intuitive way of comparing probability measures. For computational reasons, the…

机器学习 · 计算机科学 2024-03-19 Eloi Tanguy

The practical applications of Wasserstein distances (WDs) are constrained by their sample and computational complexities. Sliced-Wasserstein distances (SWDs) provide a workaround by projecting distributions onto one-dimensional subspaces,…

机器学习 · 计算机科学 2024-11-19 Huy Tran , Yikun Bai , Ashkan Shahbazi , John R. Hershey , Soheil Kolouri

The smooth 1-Wasserstein distance (SWD) $W_1^\sigma$ was recently proposed as a means to mitigate the curse of dimensionality in empirical approximation while preserving the Wasserstein structure. Indeed, SWD exhibits parametric convergence…

统计理论 · 数学 2022-02-28 Ritwik Sadhu , Ziv Goldfeld , Kengo Kato

High-dimensional data often exhibit hierarchical structures in both modes: samples and features. Yet, most existing approaches for hierarchical representation learning consider only one mode at a time. In this work, we propose an…

机器学习 · 计算机科学 2025-10-23 Ya-Wei Eileen Lin , Ronald R. Coifman , Gal Mishne , Ronen Talmon

In this work, we connect two distinct concepts for unsupervised domain adaptation: feature distribution alignment between domains by utilizing the task-specific decision boundary and the Wasserstein metric. Our proposed sliced Wasserstein…

计算机视觉与模式识别 · 计算机科学 2019-03-12 Chen-Yu Lee , Tanmay Batra , Mohammad Haris Baig , Daniel Ulbricht

To overcome computational challenges of Optimal Transport (OT), several variants of Sliced Wasserstein (SW) has been developed in the literature. These approaches exploit the closed-form expression of the univariate OT by projecting…

机器学习 · 计算机科学 2025-03-17 Hoang V. Tran , Khoi N. M. Nguyen , Trang Pham , Thanh T. Chu , Tam Le , Tan M. Nguyen

The problem of estimating the probability distribution of labels has been widely studied as a label distribution learning (LDL) problem, whose applications include age estimation, emotion analysis, and semantic segmentation. We propose a…

机器学习 · 计算机科学 2021-03-02 Ayato Toyokuni , Sho Yokoi , Hisashi Kashima , Makoto Yamada

In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions. Unfortunately, it is challenging to approximate the WD of high-dimensional…

计算机视觉与模式识别 · 计算机科学 2019-04-16 Jiqing Wu , Zhiwu Huang , Dinesh Acharya , Wen Li , Janine Thoma , Danda Pani Paudel , Luc Van Gool

In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions. Unfortunately, it is challenging to approximate the WD of high-dimensional…

计算机视觉与模式识别 · 计算机科学 2019-04-17 Jiqing Wu , Zhiwu Huang , Dinesh Acharya , Wen Li , Janine Thoma , Danda Pani Paudel , Luc Van Gool

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 properties to the…

机器学习 · 计算机科学 2019-02-04 Soheil Kolouri , Kimia Nadjahi , Umut Simsekli , Roland Badeau , Gustavo K. Rohde

Self-supervised learning is one of the most promising approaches to acquiring knowledge from limited labeled data. Despite the substantial advancements made in recent years, self-supervised models have posed a challenge to practitioners, as…

计算机视觉与模式识别 · 计算机科学 2023-12-01 Franciskus Xaverius Erick , Mina Rezaei , Johanna Paula Müller , Bernhard Kainz

Tree-Sliced methods have recently emerged as an alternative to the traditional Sliced Wasserstein (SW) distance, replacing one-dimensional lines with tree-based metric spaces and incorporating a splitting mechanism for projecting measures.…

机器学习 · 计算机科学 2025-06-10 Thanh Tran , Viet-Hoang Tran , Thanh Chu , Trang Pham , Laurent El Ghaoui , Tam Le , Tan M. Nguyen

The Weisfeiler-Lehman (WL) test is a widely used algorithm in graph machine learning, including graph kernels, graph metrics, and graph neural networks. However, it focuses only on the consistency of the graph, which means that it is unable…

机器学习 · 计算机科学 2023-05-02 Zhongxi Fang , Jianming Huang , Xun Su , Hiroyuki Kasai
‹ 上一页 1 2 3 10 下一页 ›