Synthesis and Analysis of Data as Probability Measures with Entropy-Regularized Optimal Transport

• URL: http://arxiv.org/abs/2501.07446v3
• Date: Sun, 23 Mar 2025 19:18:04 GMT
• Title: Synthesis and Analysis of Data as Probability Measures with Entropy-Regularized Optimal Transport
• Authors: Brendan Mallery, James M. Murphy, Shuchin Aeron,
• Abstract summary: We consider synthesis and analysis of probability measures using the entropy-regularized Wasserstein-2 cost and its unbiased version, the Sinkhorn divergence.<n>We show that these coefficients, as well as the value of the barycenter functional, can be estimated from samples with dimension-independent rates of convergence.<n>We employ the barycentric coefficients as features for classification of corrupted point cloud data, and show that compared to neural network baselines, our approach is more efficient in small training data regimes.
• Score: 12.573382512049053
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider synthesis and analysis of probability measures using the entropy-regularized Wasserstein-2 cost and its unbiased version, the Sinkhorn divergence. The synthesis problem consists of computing the barycenter, with respect to these costs, of reference measures given a set of coefficients belonging to the simplex. The analysis problem consists of finding the coefficients for the closest barycenter in the Wasserstein-2 distance to a given measure. Under the weakest assumptions on the measures thus far in the literature, we compute the derivative of the entropy-regularized Wasserstein-2 cost. We leverage this to establish a characterization of barycenters with respect to the entropy-regularized Wasserstein-2 cost as solutions that correspond to a fixed point of an average of the entropy-regularized displacement maps. This characterization yields a finite-dimensional, convex, quadratic program for solving the analysis problem when the measure being analyzed is a barycenter with respect to the entropy-regularized Wasserstein-2 cost. We show that these coefficients, as well as the value of the barycenter functional, can be estimated from samples with dimension-independent rates of convergence, and that barycentric coefficients are stable with respect to perturbations in the Wasserstein-2 metric. We employ the barycentric coefficients as features for classification of corrupted point cloud data, and show that compared to neural network baselines, our approach is more efficient in small training data regimes.

Related papers

• Robust Barycenter Estimation using Semi-Unbalanced Neural Optimal Transport [84.51977664336056]
  We propose a novel, scalable approach for estimating the textitrobust continuous barycenter. Our method is framed as a $min$-$max$ optimization problem and is adaptable to textitgeneral cost function.
  arXiv  Detail & Related papers  (2024-10-04T23:27:33Z)
• Computational Guarantees for Doubly Entropic Wasserstein Barycenters via Damped Sinkhorn Iterations [0.0]
  We propose and analyze an algorithm for computing doubly regularized Wasserstein barycenters. An inexact variant of our algorithm, implementable using approximate Monte Carlo sampling, offers the first non-asymptotic convergence guarantees.
  arXiv  Detail & Related papers  (2023-07-25T09:42:31Z)
• Mutual Wasserstein Discrepancy Minimization for Sequential Recommendation [82.0801585843835]
  We propose a novel self-supervised learning framework based on Mutual WasserStein discrepancy minimization MStein for the sequential recommendation. We also propose a novel contrastive learning loss based on Wasserstein Discrepancy Measurement.
  arXiv  Detail & Related papers  (2023-01-28T13:38:48Z)
• Wasserstein Archetypal Analysis [9.54262011088777]
  Archetypal analysis is an unsupervised machine learning method that summarizes data using a convex polytope. We consider an alternative formulation of archetypal analysis based on the Wasserstein metric.
  arXiv  Detail & Related papers  (2022-10-25T19:50:09Z)
• Statistical, Robustness, and Computational Guarantees for Sliced Wasserstein Distances [18.9717974398864]
  Sliced Wasserstein distances preserve properties of classic Wasserstein distances while being more scalable for computation and estimation in high dimensions. We quantify this scalability from three key aspects: (i) empirical convergence rates; (ii) robustness to data contamination; and (iii) efficient computational methods.
  arXiv  Detail & Related papers  (2022-10-17T15:04:51Z)
• Statistical Efficiency of Score Matching: The View from Isoperimetry [96.65637602827942]
  We show a tight connection between statistical efficiency of score matching and the isoperimetric properties of the distribution being estimated. We formalize these results both in the sample regime and in the finite regime.
  arXiv  Detail & Related papers  (2022-10-03T06:09:01Z)
• Variational Wasserstein Barycenters with c-Cyclical Monotonicity [17.26436842450489]
  We develop a novel continuous approximation method for the Wasserstein barycenters problem given sample access to the input distributions. We provide theoretical analysis on convergence and demonstrate the practical effectiveness of our method on real applications of posterior aggregation and synthetic data.
  arXiv  Detail & Related papers  (2021-10-22T11:06:50Z)
• Mean-Square Analysis with An Application to Optimal Dimension Dependence of Langevin Monte Carlo [60.785586069299356]
  This work provides a general framework for the non-asymotic analysis of sampling error in 2-Wasserstein distance. Our theoretical analysis is further validated by numerical experiments.
  arXiv  Detail & Related papers  (2021-09-08T18:00:05Z)
• Heavy-tailed Streaming Statistical Estimation [58.70341336199497]
  We consider the task of heavy-tailed statistical estimation given streaming $p$ samples. We design a clipped gradient descent and provide an improved analysis under a more nuanced condition on the noise of gradients.
  arXiv  Detail & Related papers  (2021-08-25T21:30:27Z)
• Entanglement Entropy of Non-Hermitian Free Fermions [59.54862183456067]
  We study the entanglement properties of non-Hermitian free fermionic models with translation symmetry. Our results show that the entanglement entropy has a logarithmic correction to the area law in both one-dimensional and two-dimensional systems.
  arXiv  Detail & Related papers  (2021-05-20T14:46:09Z)
• Streaming computation of optimal weak transport barycenters [13.664682865991255]
  We provide a theoretical analysis of the weak barycenter and its relationship to the classic Wasserstein barycenter. We provide iterative algorithms to compute a weak barycenter for either finite or infinite families of arbitrary measures.
  arXiv  Detail & Related papers  (2021-02-26T10:08:02Z)
• Learning High Dimensional Wasserstein Geodesics [55.086626708837635]
  We propose a new formulation and learning strategy for computing the Wasserstein geodesic between two probability distributions in high dimensions. By applying the method of Lagrange multipliers to the dynamic formulation of the optimal transport (OT) problem, we derive a minimax problem whose saddle point is the Wasserstein geodesic. We then parametrize the functions by deep neural networks and design a sample based bidirectional learning algorithm for training.
  arXiv  Detail & Related papers  (2021-02-05T04:25:28Z)
• Continuous Wasserstein-2 Barycenter Estimation without Minimax Optimization [94.18714844247766]
  Wasserstein barycenters provide a geometric notion of the weighted average of probability measures based on optimal transport. We present a scalable algorithm to compute Wasserstein-2 barycenters given sample access to the input measures.
  arXiv  Detail & Related papers  (2021-02-02T21:01:13Z)
• Continuous Regularized Wasserstein Barycenters [51.620781112674024]
  We introduce a new dual formulation for the regularized Wasserstein barycenter problem. We establish strong duality and use the corresponding primal-dual relationship to parametrize the barycenter implicitly using the dual potentials of regularized transport problems.
  arXiv  Detail & Related papers  (2020-08-28T08:28:06Z)
• Disentangled Representation Learning with Wasserstein Total Correlation [90.44329632061076]
  We introduce Wasserstein total correlation in both variational autoencoder and Wasserstein autoencoder settings to learn disentangled latent representations. A critic is adversarially trained along with the main objective to estimate the Wasserstein total correlation term. We show that the proposed approach has comparable performances on disentanglement with smaller sacrifices in reconstruction abilities.
  arXiv  Detail & Related papers  (2019-12-30T05:31:28Z)

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.