Estimation of Stochastic Optimal Transport Maps

• URL: http://arxiv.org/abs/2512.09499v1
• Date: Wed, 10 Dec 2025 10:23:40 GMT
• Title: Estimation of Stochastic Optimal Transport Maps
• Authors: Sloan Nietert, Ziv Goldfeld,
• Abstract summary: We introduce a novel metric for evaluating the transportation quality of maps.<n>Under this metric, we develop computationally efficient map estimators with near-optimal finite-sample risk bounds.<n>These contributions constitute the first general-purpose theory for map estimation, compatible with a wide spectrum of real-world applications.
• Score: 20.559434126392205
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The optimal transport (OT) map is a geometry-driven transformation between high-dimensional probability distributions which underpins a wide range of tasks in statistics, applied probability, and machine learning. However, existing statistical theory for OT map estimation is quite restricted, hinging on Brenier's theorem (quadratic cost, absolutely continuous source) to guarantee existence and uniqueness of a deterministic OT map, on which various additional regularity assumptions are imposed to obtain quantitative error bounds. In many real-world problems these conditions fail or cannot be certified, in which case optimal transportation is possible only via stochastic maps that can split mass. To broaden the scope of map estimation theory to such settings, this work introduces a novel metric for evaluating the transportation quality of stochastic maps. Under this metric, we develop computationally efficient map estimators with near-optimal finite-sample risk bounds, subject to easy-to-verify minimal assumptions. Our analysis further accommodates common forms of adversarial sample contamination, yielding estimators with robust estimation guarantees. Empirical experiments are provided which validate our theory and demonstrate the utility of the proposed framework in settings where existing theory fails. These contributions constitute the first general-purpose theory for map estimation, compatible with a wide spectrum of real-world applications where optimal transport may be intrinsically stochastic.

Related papers

• On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization [57.179679246370114]
  A potential limitation of existing methods is the bias inherent in most perturbation estimators unless a stepsize is proposed.<n>We propose a novel family of unbiased gradient scaling estimators that eliminate bias while maintaining favorable construction.
  arXiv  Detail & Related papers  (2025-10-22T18:25:43Z)
• Stability Bounds for Smooth Optimal Transport Maps and their Statistical Implications [16.906924555293916]
  We focus on plugin estimators derived from the optimal transport (OT) map between two probability distributions.<n>We develop novel stability bounds for OT maps which generalize those in past work.<n>As an illustrative application, we develop and analyze a novel tuning parameter-free estimator for the OT map between two strongly log-concave distributions.
  arXiv  Detail & Related papers  (2025-02-17T21:17:03Z)
• Statistical Convergence Rates of Optimal Transport Map Estimation between General Distributions [8.326725299573754]
  We aim to broaden the scope of OT map estimation and fill this gap between theory and practice.<n>We introduce a sieve plug-in estimator and establish its convergence rates without the strong convexity assumption on Brenier's potential.<n>We also develop scalable algorithms to efficiently solve the OT map estimation using neural networks.
  arXiv  Detail & Related papers  (2024-12-11T03:18:17Z)
• Minimax estimation of discontinuous optimal transport maps: The semi-discrete case [14.333765302506658]
  We consider the problem of estimating the optimal transport map between two probability distributions, $P$ and $Q$ in $mathbb Rd$. We show that an estimator based on entropic optimal transport converges at the minimax-optimal rate $n-1/2$, independent of dimension.
  arXiv  Detail & Related papers  (2023-01-26T18:41:38Z)
• GAN Estimation of Lipschitz Optimal Transport Maps [0.0]
  This paper introduces the first statistically consistent estimator of the optimal transport map between two probability distributions, based on neural networks. We demonstrate that, under regularity assumptions, the obtained generator converges uniformly to the optimal transport map as the sample size increases to infinity. In contrast to previous work tackling either statistical guarantees or practicality, we provide an expressive and feasible estimator which paves way for optimal transport applications.
  arXiv  Detail & Related papers  (2022-02-16T10:15:56Z)
• Random Forest Weighted Local Fréchet Regression with Random Objects [18.128663071848923]
  We propose a novel random forest weighted local Fr'echet regression paradigm.<n>Our first method uses these weights as the local average to solve the conditional Fr'echet mean.<n>Second method performs local linear Fr'echet regression, both significantly improving existing Fr'echet regression methods.
  arXiv  Detail & Related papers  (2022-02-10T09:10:59Z)
• Optimal variance-reduced stochastic approximation in Banach spaces [114.8734960258221]
  We study the problem of estimating the fixed point of a contractive operator defined on a separable Banach space. We establish non-asymptotic bounds for both the operator defect and the estimation error.
  arXiv  Detail & Related papers  (2022-01-21T02:46:57Z)
• Near-optimal estimation of smooth transport maps with kernel sums-of-squares [81.02564078640275]
  Under smoothness conditions, the squared Wasserstein distance between two distributions could be efficiently computed with appealing statistical error upper bounds. The object of interest for applications such as generative modeling is the underlying optimal transport map. We propose the first tractable algorithm for which the statistical $L2$ error on the maps nearly matches the existing minimax lower-bounds for smooth map estimation.
  arXiv  Detail & Related papers  (2021-12-03T13:45:36Z)
• Comparing Probability Distributions with Conditional Transport [63.11403041984197]
  We propose conditional transport (CT) as a new divergence and approximate it with the amortized CT (ACT) cost. ACT amortizes the computation of its conditional transport plans and comes with unbiased sample gradients that are straightforward to compute. On a wide variety of benchmark datasets generative modeling, substituting the default statistical distance of an existing generative adversarial network with ACT is shown to consistently improve the performance.
  arXiv  Detail & Related papers  (2020-12-28T05:14:22Z)
• Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation [99.92568326314667]
  We propose the amortized conditional normalized maximum likelihood (ACNML) method as a scalable general-purpose approach for uncertainty estimation. Our algorithm builds on the conditional normalized maximum likelihood (CNML) coding scheme, which has minimax optimal properties according to the minimum description length principle. We demonstrate that ACNML compares favorably to a number of prior techniques for uncertainty estimation in terms of calibration on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2020-11-05T08:04:34Z)
• Statistical Optimal Transport posed as Learning Kernel Embedding [0.0]
  This work takes the novel approach of posing statistical Optimal Transport (OT) as that of learning the transport plan's kernel mean embedding from sample based estimates of marginal embeddings. A key result is that, under very mild conditions, $epsilon$-optimal recovery of the transport plan as well as the Barycentric-projection based transport map is possible with a sample complexity that is completely dimension-free.
  arXiv  Detail & Related papers  (2020-02-08T14:58:53Z)
• Distributionally Robust Bayesian Quadrature Optimization [60.383252534861136]
  We study BQO under distributional uncertainty in which the underlying probability distribution is unknown except for a limited set of its i.i.d. samples. A standard BQO approach maximizes the Monte Carlo estimate of the true expected objective given the fixed sample set. We propose a novel posterior sampling based algorithm, namely distributionally robust BQO (DRBQO) for this purpose.
  arXiv  Detail & Related papers  (2020-01-19T12:00:33Z)

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.