paper-with-me

Papers

Tree-Sliced Variants of Wasserstein Distances

2019-02-01 · NeurIPS 2019 12 · Tam Le, Makoto Yamada, Kenji Fukumizu, Marco Cuturi

Optimal transport (\OT) theory defines a powerful set of tools to compare probability distributions. \OT~suffers however from a few drawbacks, computational and statistical, which have encouraged the proposal of several regularized variants of OT in the recent literature, one of the most notable being the \textit{sliced} formulation, which exploits the closed-form formula between univariate distributions by projecting high-dimensional measures onto random lines. We consider in this work a more general family of ground metrics, namely \textit{tree metrics}, which also yield fast closed-form computations and negative definite, and of which the sliced-Wasserstein distance is a particular case (the tree is a chain). We propose the tree-sliced Wasserstein distance, computed by averaging the Wasserstein distance between these measures using random tree metrics, built adaptively in either low or high-dimensional spaces. Exploiting the negative definiteness of that distance, we also propose a positive definite kernel, and test it against other baselines on a few benchmark tasks.

📄 PDF Abstract BibTeX arXiv:1902.00342

Code (2)

lttam/TreeWasserstein 공식 구현
InkToYou/TreeWasserstein

Similar Papers 제목 키워드 기반

Augmented Sliced Wasserstein Distances

2020-06-15 · ICLR 2022 4 · Xiongjie Chen, Yongxin Yang, Yunpeng Li

While theoretically appealing, the application of the Wasserstein distance to large-scale machine learning problems has been hampered by its prohibitive computational cost. The sliced Wasserstein distance and its variant…

Computational Efficiencyvalid

Point-set Distances for Learning Representations of 3D Point Clouds

2021-02-08 · ICCV 2021 10 · Trung Nguyen, Quang-Hieu Pham, Tam Le, Tung Pham 외

Learning an effective representation of 3D point clouds requires a good metric to measure the discrepancy between two 3D point sets, which is non-trivial due to their irregularity. Most of the previous works resort to us…

Point Cloud RegistrationTransfer Learning

Markovian Sliced Wasserstein Distances: Beyond Independent Projections

2023-01-10 · NeurIPS 2023 11 · Khai Nguyen, Tongzheng Ren, Nhat Ho

Sliced Wasserstein (SW) distance suffers from redundant projections due to independent uniform random projecting directions. To partially overcome the issue, max K sliced Wasserstein (Max-K-SW) distance ($K\geq 1$), seek…

Understanding Learning with Sliced-Wasserstein Requires Rethinking Informative Slices

2024-11-16 · Huy Tran, Yikun Bai, Ashkan Shahbazi, John R. Hershey 외

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-dime…

Informativeness

Tree-Sliced Wasserstein Distance: A Geometric Perspective

2024-06-19 · Viet-Hoang Tran, Trang Pham, Tho Tran, Minh Khoi Nguyen Nhat 외

Many variants of Optimal Transport (OT) have been developed to address its heavy computation. Among them, notably, Sliced Wasserstein (SW) is widely used for application domains by projecting the OT problem onto one-dime…

Computational EfficiencyStyle Transfer