Hierarchical Hybrid Sliced Wasserstein: A Scalable Metric for Heterogeneous Joint Distributions

• URL: http://arxiv.org/abs/2404.15378v3
• Date: Tue, 08 Oct 2024 01:39:18 GMT
• Title: Hierarchical Hybrid Sliced Wasserstein: A Scalable Metric for Heterogeneous Joint Distributions
• Authors: Khai Nguyen, Nhat Ho,
• Abstract summary: Sliced Wasserstein (SW) and Generalized Sliced Wasserstein (GSW) have been widely used in applications due to their computational and statistical scalability. We propose two new slicing operators i.e., Partial Generalized Radon Transform (PGRT) and Hierarchical Hybrid Radon Transform (HHRT) By using HHRT, we extend the SW into Hierarchical Hybrid Sliced Wasserstein (H2SW) distance which is designed specifically for comparing heterogeneous joint distributions.
• Score: 39.94228953940542
• License:
• Abstract: Sliced Wasserstein (SW) and Generalized Sliced Wasserstein (GSW) have been widely used in applications due to their computational and statistical scalability. However, the SW and the GSW are only defined between distributions supported on a homogeneous domain. This limitation prevents their usage in applications with heterogeneous joint distributions with marginal distributions supported on multiple different domains. Using SW and GSW directly on the joint domains cannot make a meaningful comparison since their homogeneous slicing operator i.e., Radon Transform (RT) and Generalized Radon Transform (GRT) are not expressive enough to capture the structure of the joint supports set. To address the issue, we propose two new slicing operators i.e., Partial Generalized Radon Transform (PGRT) and Hierarchical Hybrid Radon Transform (HHRT). In greater detail, PGRT is the generalization of Partial Radon Transform (PRT), which transforms a subset of function arguments non-linearly while HHRT is the composition of PRT and multiple domain-specific PGRT on marginal domain arguments. By using HHRT, we extend the SW into Hierarchical Hybrid Sliced Wasserstein (H2SW) distance which is designed specifically for comparing heterogeneous joint distributions. We then discuss the topological, statistical, and computational properties of H2SW. Finally, we demonstrate the favorable performance of H2SW in 3D mesh deformation, deep 3D mesh autoencoders, and datasets comparison.

Related papers

• Deep Diversity-Enhanced Feature Representation of Hyperspectral Images [87.47202258194719]
  We rectify 3D convolution by modifying its topology to enhance the rank upper-bound. We also propose a novel diversity-aware regularization (DA-Reg) term that acts on the feature maps to maximize independence among elements. To demonstrate the superiority of the proposed Re$3$-ConvSet and DA-Reg, we apply them to various HS image processing and analysis tasks.
  arXiv  Detail & Related papers  (2023-01-15T16:19:18Z)
• Markovian Sliced Wasserstein Distances: Beyond Independent Projections [51.80527230603978]
  We introduce a new family of SW distances, named Markovian sliced Wasserstein (MSW) distance, which imposes a first-order Markov structure on projecting directions. We compare distances with previous SW variants in various applications such as flows, color transfer, and deep generative modeling to demonstrate the favorable performance of MSW.
  arXiv  Detail & Related papers  (2023-01-10T01:58:15Z)
• Hierarchical Sliced Wasserstein Distance [27.12983497199479]
  Sliced Wasserstein (SW) distance can be scaled to a large number of supports without suffering from the curse of dimensionality. Despite its efficiency in the number of supports, estimating the sliced Wasserstein requires a relatively large number of projections in high-dimensional settings. We propose to derive projections by linearly and randomly combining a smaller number of projections which are named bottleneck projections. We then formulate the approach into a new metric between measures, named Hierarchical Sliced Wasserstein (HSW) distance.
  arXiv  Detail & Related papers  (2022-09-27T17:46:15Z)
• Asymmetric Transfer Hashing with Adaptive Bipartite Graph Learning [95.54688542786863]
  Existing hashing methods assume that the query and retrieval samples lie in homogeneous feature space within the same domain. We propose an Asymmetric Transfer Hashing (ATH) framework with its unsupervised/semi-supervised/supervised realizations. By jointly optimizing asymmetric hash functions and the bipartite graph, not only can knowledge transfer be achieved but information loss caused by feature alignment can also be avoided.
  arXiv  Detail & Related papers  (2022-06-25T08:24:34Z)
• Orthogonal Gromov-Wasserstein Discrepancy with Efficient Lower Bound [11.086440815804226]
  The Gromov-Wasserstein (GW) formulates a node graph between the structured data based on optimal transportation datasets. We take inspiration from the connection with the assignment problem, and propose the Gromov-Wasserstein discrepancy as a surrogate of GW.
  arXiv  Detail & Related papers  (2022-05-12T02:10:56Z)
• Batch Normalization Orthogonalizes Representations in Deep Random Networks [3.109481609083199]
  We establish a non-asymptotic characterization of the interplay between depth, width, and the orthogonality of deep representations. We prove that the deviation of the representations from orthogonality rapidly decays with depth up to a term inversely proportional to the network width. This result has two main implications: 1) Theoretically, as the depth grows, the distribution of the representation contracts to a Wasserstein-2 ball around an isotropic Gaussian distribution.
  arXiv  Detail & Related papers  (2021-06-07T21:14:59Z)
• Finite sample approximations of exact and entropic Wasserstein distances between covariance operators and Gaussian processes [0.0]
  We show that the Sinkhorn divergence between two centered Gaussian processes can be consistently and efficiently estimated. For a fixed regularization parameter, the convergence rates are it dimension-independent and of the same order as those for the Hilbert-Schmidt distance. If at least one of the RKHS is finite-dimensional, we obtain a it dimension-dependent sample complexity for the exact Wasserstein distance between the Gaussian processes.
  arXiv  Detail & Related papers  (2021-04-26T06:57:14Z)
• Improving Relational Regularized Autoencoders with Spherical Sliced Fused Gromov Wasserstein [29.527406546511298]
  We propose a new relational discrepancy named spherical sliced fused Gromov Wasserstein (SSFG) We show that the new proposed autoencoders have favorable performance in learning latent manifold structure, image generation, and reconstruction.
  arXiv  Detail & Related papers  (2020-10-05T05:26:50Z)
• Region adaptive graph fourier transform for 3d point clouds [51.193111325231165]
  We introduce the Region Adaptive Graph Fourier Transform (RA-GFT) for compression of 3D point cloud attributes. The RA-GFT achieves better complexity-performance trade-offs than previous approaches.
  arXiv  Detail & Related papers  (2020-03-04T02:47:44Z)
• Fast and Robust Comparison of Probability Measures in Heterogeneous Spaces [62.35667646858558]
  We introduce the Anchor Energy (AE) and Anchor Wasserstein (AW) distances, which are respectively the energy and Wasserstein distances instantiated on such representations. Our main contribution is to propose a sweep line algorithm to compute AE emphexactly in log-quadratic time, where a naive implementation would be cubic. We show that AE and AW perform well in various experimental settings at a fraction of the computational cost of popular GW approximations.
  arXiv  Detail & Related papers  (2020-02-05T03:09:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.