Statistical Inference for Optimal Transport Maps: Recent Advances and Perspectives

• URL: http://arxiv.org/abs/2506.19025v1
• Date: Mon, 23 Jun 2025 18:28:48 GMT
• Title: Statistical Inference for Optimal Transport Maps: Recent Advances and Perspectives
• Authors: Sivaraman Balakrishnan, Tudor Manole, Larry Wasserman,
• Abstract summary: In many applications of optimal transport (OT), the object of primary interest is the optimal transport map.<n>This map rearranges mass from one probability distribution to another in the most efficient way possible by minimizing a specified cost.<n>We review recent advances in estimating and developing limit theorems for the OT map, using samples from the underlying distributions.
• Score: 15.043089053838013
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In many applications of optimal transport (OT), the object of primary interest is the optimal transport map. This map rearranges mass from one probability distribution to another in the most efficient way possible by minimizing a specified cost. In this paper we review recent advances in estimating and developing limit theorems for the OT map, using samples from the underlying distributions. We also review parallel lines of work that establish similar results for special cases and variants of the basic OT setup. We conclude with a discussion of key directions for future research with the goal of providing practitioners with reliable inferential tools.

Related papers

• Embedding Empirical Distributions for Computing Optimal Transport Maps [20.78001177211786]
  We introduce a novel approach to learning transport maps for new empirical distributions.<n>We employ the transformer architecture to produce embeddings from distributional data of varying length.<n>These embeddings are then fed into a hypernetwork to generate neural OT maps.
  arXiv  Detail & Related papers  (2025-04-24T16:52:48Z)
• Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan [5.374547520354591]
  Semi-dual Neural OT, a widely used approach for learning OT Maps with neural networks, often generates spurious solutions that fail to transfer one distribution to another accurately.<n>We propose a novel method, OTP, which learns both the OT Map and the Optimal Transport Plan, representing the optimal coupling between two distributions.<n>Our experiments show that the OTP model recovers the optimal transport map where existing methods fail and outperforms current OT-based models in image-to-image translation tasks.
  arXiv  Detail & Related papers  (2025-02-07T00:37:12Z)
• A Statistical Learning Perspective on Semi-dual Adversarial Neural Optimal Transport Solvers [65.28989155951132]
  In this paper, we establish upper bounds on the generalization error of an approximate OT map recovered by the minimax quadratic OT solver.<n>While our analysis focuses on the quadratic OT, we believe that similar bounds could be derived for general OT case, paving the promising direction for future research.
  arXiv  Detail & Related papers  (2025-02-03T12:37:20Z)
• Estimating Barycenters of Distributions with Neural Optimal Transport [93.28746685008093]
  We propose a new scalable approach for solving the Wasserstein barycenter problem. Our methodology is based on the recent Neural OT solver. We also establish theoretical error bounds for our proposed approach.
  arXiv  Detail & Related papers  (2024-02-06T09:17:07Z)
• Double-Bounded Optimal Transport for Advanced Clustering and Classification [58.237576976486544]
  We propose Doubly Bounded Optimal Transport (DB-OT), which assumes that the target distribution is restricted within two boundaries instead of a fixed one. We show that our method can achieve good results with our improved inference scheme in the testing stage.
  arXiv  Detail & Related papers  (2024-01-21T07:43:01Z)
• Analyzing and Improving Optimal-Transport-based Adversarial Networks [9.980822222343921]
  Optimal Transport (OT) problem aims to find a transport plan that bridges two distributions while minimizing a given cost function. OT theory has been widely utilized in generative modeling. Our approach achieves a FID score of 2.51 on CIFAR-10 and 5.99 on CelebA-HQ-256, outperforming unified OT-based adversarial approaches.
  arXiv  Detail & Related papers  (2023-10-04T06:52:03Z)
• Keypoint-Guided Optimal Transport [85.396726225935]
  We propose a novel KeyPoint-Guided model by ReLation preservation (KPG-RL) that searches for the optimal matching. The proposed KPG-RL model can be solved by Sinkhorn's algorithm and is applicable even when distributions are supported in different spaces. Based on the learned transport plan from dual KPG-RL, we propose a novel manifold barycentric projection to transport source data to the target domain.
  arXiv  Detail & Related papers  (2023-03-23T08:35:56Z)
• Low-rank Optimal Transport: Approximation, Statistics and Debiasing [51.50788603386766]
  Low-rank optimal transport (LOT) approach advocated in citescetbon 2021lowrank LOT is seen as a legitimate contender to entropic regularization when compared on properties of interest. We target each of these areas in this paper in order to cement the impact of low-rank approaches in computational OT.
  arXiv  Detail & Related papers  (2022-05-24T20:51:37Z)
• 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)
• Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark [133.46066694893318]
  We evaluate the performance of neural network-based solvers for optimal transport. We find that existing solvers do not recover optimal transport maps even though they perform well in downstream tasks.
  arXiv  Detail & Related papers  (2021-06-03T15:59:28Z)
• Minibatch optimal transport distances; analysis and applications [9.574645423576932]
  Optimal transport distances have become a classic tool to compare probability distributions and have found many applications in machine learning. A common workaround is to compute these distances on minibatches to average the outcome of several smaller optimal transport problems. We propose in this paper an extended analysis of this practice, which effects were previously studied in restricted cases.
  arXiv  Detail & Related papers  (2021-01-05T21:29:31Z)
• 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)

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.