Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation

• URL: http://arxiv.org/abs/2602.04335v1
• Date: Wed, 04 Feb 2026 08:56:28 GMT
• Title: Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation
• Authors: Ferdinand Genans, Olivier Wintenberger,
• Abstract summary: We introduce a tuning-free estimator of $textOT_c(, hat)$ that utilizes the semi-dual OT functional and, remarkably, requires no OT solver.<n>This framework unlocks significant computational and statistical advantages in practice.<n> Numerical experiments demonstrate that our geometry-aware pipeline effectively mitigates the discretization error bottleneck.
• Score: 32.357350666094156
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Solving large scale Optimal Transport (OT) in machine learning typically relies on sampling measures to obtain a tractable discrete problem. While the discrete solver's accuracy is controllable, the rate of convergence of the discretization error is governed by the intrinsic dimension of our data. Therefore, the true bottleneck is the knowledge and control of the sampling error. In this work, we tackle this issue by introducing novel estimators for both sampling error and intrinsic dimension. The key finding is a simple, tuning-free estimator of $\text{OT}_c(ρ, \hatρ)$ that utilizes the semi-dual OT functional and, remarkably, requires no OT solver. Furthermore, we derive a fast intrinsic dimension estimator from the multi-scale decay of our sampling error estimator. This framework unlocks significant computational and statistical advantages in practice, enabling us to (i) quantify the convergence rate of the discretization error, (ii) calibrate the entropic regularization of Sinkhorn divergences to the data's intrinsic geometry, and (iii) introduce a novel, intrinsic-dimension-based Richardson extrapolation estimator that strongly debiases Wasserstein distance estimation. Numerical experiments demonstrate that our geometry-aware pipeline effectively mitigates the discretization error bottleneck while maintaining computational efficiency.

Related papers

• Dimension-free error estimate for diffusion model and optimal scheduling [22.20348860913421]
  Diffusion generative models have emerged as powerful tools for producing synthetic data from an empirically observed distribution.<n>Previous analyses have quantified the error between the generated and the true data distributions in terms of Wasserstein distance or Kullback-Leibler divergence.<n>In this work, we derive an explicit, dimension-free bound on the discrepancy between the generated and the true data distributions.
  arXiv  Detail & Related papers  (2025-12-01T15:58:20Z)
• Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching [60.37045080890305]
  We provide the first analysis of the sample complexity for flow-matching based generative models.<n>We decompose the velocity field estimation error into neural-network approximation error, statistical error due to the finite sample size, and optimization error due to the finite number of optimization steps for estimating the velocity field.
  arXiv  Detail & Related papers  (2025-12-01T05:14:25Z)
• Efficient Covariance Estimation for Sparsified Functional Data [51.69796254617083]
  proposed Random-knots (Random-knots-Spatial) and B-spline (Bspline-Spatial) estimators of the covariance function are computationally efficient.<n>Asymptotic pointwise of the covariance are obtained for sparsified individual trajectories under some regularity conditions.
  arXiv  Detail & Related papers  (2025-11-23T00:50:33Z)
• Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations [57.179679246370114]
  We identify the distribution of random perturbations that minimizes the estimator's variance as the perturbation stepsize tends to zero.<n>Our findings reveal that such desired perturbations can align directionally with the true gradient, instead of maintaining a fixed length.
  arXiv  Detail & Related papers  (2025-10-22T19:06:39Z)
• 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)
• Distributed Estimation and Inference for Semi-parametric Binary Response Models [8.309294338998539]
  This paper studies the maximum score estimator of a semi-parametric binary choice model under a distributed computing environment. An intuitive divide-and-conquer estimator is computationally expensive and restricted by a non-regular constraint on the number of machines.
  arXiv  Detail & Related papers  (2022-10-15T23:06:46Z)
• Asymptotically Unbiased Instance-wise Regularized Partial AUC Optimization: Theory and Algorithm [101.44676036551537]
  One-way Partial AUC (OPAUC) and Two-way Partial AUC (TPAUC) measures the average performance of a binary classifier. Most of the existing methods could only optimize PAUC approximately, leading to inevitable biases that are not controllable. We present a simpler reformulation of the PAUC problem via distributional robust optimization AUC.
  arXiv  Detail & Related papers  (2022-10-08T08:26:22Z)
• Learning interaction kernels in stochastic systems of interacting particles from multiple trajectories [13.3638879601361]
  We consider systems of interacting particles or agents, with dynamics determined by an interaction kernel. We introduce a nonparametric inference approach to this inverse problem, based on a regularized maximum likelihood estimator. We show that a coercivity condition enables us to control the condition number of this problem and prove the consistency of our estimator.
  arXiv  Detail & Related papers  (2020-07-30T01:28:06Z)
• Faster Wasserstein Distance Estimation with the Sinkhorn Divergence [0.0]
  The squared Wasserstein distance is a quantity to compare probability distributions in a non-parametric setting. In this work, we propose instead to estimate it with the Sinkhorn divergence. We show that, for smooth densities, this estimator has a comparable sample complexity but allows higher regularization levels.
  arXiv  Detail & Related papers  (2020-06-15T06:58:16Z)
• $\gamma$-ABC: Outlier-Robust Approximate Bayesian Computation Based on a Robust Divergence Estimator [95.71091446753414]
  We propose to use a nearest-neighbor-based $gamma$-divergence estimator as a data discrepancy measure. Our method achieves significantly higher robustness than existing discrepancy measures.
  arXiv  Detail & Related papers  (2020-06-13T06:09:27Z)
• Neural Control Variates [71.42768823631918]
  We show that a set of neural networks can face the challenge of finding a good approximation of the integrand. We derive a theoretically optimal, variance-minimizing loss function, and propose an alternative, composite loss for stable online training in practice. Specifically, we show that the learned light-field approximation is of sufficient quality for high-order bounces, allowing us to omit the error correction and thereby dramatically reduce the noise at the cost of negligible visible bias.
  arXiv  Detail & Related papers  (2020-06-02T11:17:55Z)

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.