CyclOT: Learning Quadratic Optimal Transport Maps via Synchronized Forward-Backward Interpolants

• URL: http://arxiv.org/abs/2609.13892v1
• Date: Sat, 12 Sep 2026 11:31:53 GMT
• Title: CyclOT: Learning Quadratic Optimal Transport Maps via Synchronized Forward-Backward Interpolants
• Abstract summary: We introduce a bidirectional neural framework in which the learned maps induce forward and backward displacement interpolants.<n>Experiments on Swiss roll, MNIST, CelebA, single-cell data, and chest X-ray images evaluate endpoint fidelity, transport cost inverse, consistency, and the geometry of the induced inverts.
• Score: 20.064386074670605
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the recovery of forward and reverse quadratic optimal-transport maps from unpaired samples in high dimensions. We introduce a bidirectional neural framework in which the learned maps induce forward and backward displacement interpolants, while the training objective combines bidirectional quadratic action, discriminator-restricted Jensen-Shannon endpoint objectives, and two-sided cycle consistency. The construction requires neither precomputed sample pairings nor an explicit convex-potential parameterization. For absolutely continuous probability measures supported on a compact convex set, and under the stated generator-approximation, discriminator-richness, and minimizer-attainment conditions, we prove a population recovery theorem: for every prescribed accuracy, the sum of the corresponding \(L^2\) errors between any global minimizer and the forward and reverse quadratic Brenier maps is below that accuracy, provided the discriminator level is sufficiently large and the annealing action weight becomes sufficiently small. Moreover, the cycle loss is bounded above by \(λW_2^2(μ_0,μ_1)\). Complementary results quantify approximate invertibility and show that exact endpoint Jensen-Shannon divergence and cycle consistency control missing target mass and many-to-one map collapse, respectively. Experiments on Swiss roll, MNIST, CelebA, single-cell perturbation data, and chest X-ray images evaluate endpoint fidelity, transport cost, inverse consistency, and the geometry of the induced interpolations.

Related papers

• Predicting When Random Low-Dimensional Reparameterizations Train Neural Networks [3.980892205755342]
  We present an orientation-resolved quadratic master formula that predicts the random-slice residual from both the curvature spectrum and the reference-to-solution displacement profile.<n>We then introduce Random Mapping Networks (RaMaN), which instantiate the predicted latent dimension using structured Hadamard or seed-regenerated Gaussian maps.<n>RaMaN closely tracks measured transition locations and outperforms orientation-agnostic approximations when displacement direction matters.
  arXiv  Detail & Related papers  (2026-08-12T21:09:54Z)
• Stability Annealing Selects the Implicit Bias of Smoothed Sign Descent: A Rate-Indexed Barrier Path on Separable Data [3.7437735326653883]
  This paper studies the rate-controlled middle case for full-batch linear classification on separable data.<n>For memoryless stability-annealed smoothed-sign descent with weighted exponential loss, we prove that the normalized iterates converge to the minimizer of a convex Burg-type barrier over a margin slice.
  arXiv  Detail & Related papers  (2026-07-07T08:55:35Z)
• Semidefinite Relaxations for Collision-Free Motion Planning [53.160637667144876]
  We focus on a point robot moving from start to goal through inmathbbRn constraints in terms of $C4 trajectories.<n>We demonstrate its effectiveness as a planner for minimum-snap continuous planning with $C4 trajectories.
  arXiv  Detail & Related papers  (2026-06-12T03:18:03Z)
• Barycentric Projections of Optimal Transport Plans on Riemannian Manifolds [0.31727619150610836]
  We develop a framework for barycentric projections of transport couplings.<n>In intrinsic projection maps each source point to the conditional Fréchet mean of its destination law.<n>For discrete couplings, both constructions decompose row-wise into weighted Fréchet mean and log-exp problems.
  arXiv  Detail & Related papers  (2026-06-06T01:31:58Z)
• Fitting Unknown Number of Hyperplanes with Manifold Optimization [57.48093263119306]
  Fitting unknown number of linearplanes to data is a fundamental yet challenging problem in machine learning.<n>Existing approaches often struggle with optimum optima or lack geometric consistency.
  arXiv  Detail & Related papers  (2026-05-27T14:02:20Z)
• Amortized Energy-Based Bayesian Inference [5.330852012059025]
  We propose a transport-based approach that learns an observation-dependent map pushing forward a reference measure to approximate the posterior distribution.<n>This formulation is likelihood-free, requiring only joint samples, and avoids density evaluation, invertibility constraints, and Jacobian computations.<n>We illustrate the method on a finite-dimensional nonlinear inverse problem and two PDE-constrained inverse problems arising in porous medium flow and seismic inversion.
  arXiv  Detail & Related papers  (2026-05-14T20:45:11Z)
• 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)
• Bayesian Circular Regression with von Mises Quasi-Processes [57.88921637944379]
  In this work we explore a family of expressive and interpretable distributions over circle-valued random functions.<n>For posterior inference, we introduce a new Stratonovich-like augmentation that lends itself to fast Gibbs sampling.<n>We present experiments applying this model to the prediction of wind directions and the percentage of the running gait cycle as a function of joint angles.
  arXiv  Detail & Related papers  (2024-06-19T01:57:21Z)
• Sampling and estimation on manifolds using the Langevin diffusion [45.57801520690309]
  Two estimators of linear functionals of $mu_phi $ based on the discretized Markov process are considered.<n>Error bounds are derived for sampling and estimation using a discretization of an intrinsically defined Langevin diffusion.
  arXiv  Detail & Related papers  (2023-12-22T18:01:11Z)
• 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)

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.