Fixed-Point Neural Optimal Transport without Implicit Differentiation

• URL: http://arxiv.org/abs/2605.10792v1
• Date: Mon, 11 May 2026 16:22:06 GMT
• Title: Fixed-Point Neural Optimal Transport without Implicit Differentiation
• Abstract summary: We propose an implicit neural formulation of optimal transport that eliminates adversarial min-max optimization and multi-network architectures.<n>Our key idea is to parameterize a single potential in the Kantorovich dual and reformulate the associated c-transform as a proximal fixed-point problem.<n>This yields a stable single-network framework in which dual feasibility is enforced exactly through proximal optimality conditions.
• Score: 3.4298729855744026
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose an implicit neural formulation of optimal transport that eliminates adversarial min--max optimization and multi-network architectures commonly used in existing approaches. Our key idea is to parameterize a single potential in the Kantorovich dual and reformulate the associated c-transform as a proximal fixed-point problem. This yields a stable single-network framework in which dual feasibility is enforced exactly through proximal optimality conditions rather than adversarial training. Despite the inner fixed-point computation, gradients can be computed without differentiating through the fixed-point iterations, enabling efficient training without requiring implicit differentiation. We further establish convergence of stochastic gradient descent. The resulting framework is efficient, scalable, and broadly applicable: it simultaneously recovers forward and backward transport maps and naturally extends to class-conditional settings. Experiments on high-dimensional Gaussian benchmarks, physical datasets, and image translation tasks demonstrate strong transport accuracy together with improved training stability and favorable computational and memory efficiency.

Related papers

• Universal Smoothness via Bernstein Polynomials: A Constructive Approximation Approach for Activation Functions [16.856453018275467]
  The efficacy of deep neural networks is heavily reliant on the design of non-linear activation functions.<n>The proposed method guarantees strictly continuous differentiability and a non-expansive Lipschitz constant of one.<n>This approach consistently outperforms state-of-the-art baselines on standard image classification benchmarks.
  arXiv  Detail & Related papers  (2026-05-04T13:38:16Z)
• Variational Entropic Optimal Transport [67.76725267984578]
  We propose Variational Entropic Optimal Transport (VarEOT) for domain translation problems.<n>VarEOT is based on an exact variational reformulation of the log-partition $log mathbbE[exp(cdot)$ as a tractable generalization over an auxiliary positive normalizer.<n> Experiments on synthetic data and unpaired image-to-image translation demonstrate competitive or improved translation quality.
  arXiv  Detail & Related papers  (2026-02-02T15:48:44Z)
• Neural Optimal Transport Meets Multivariate Conformal Prediction [58.43397908730771]
  We propose a framework for conditional vectorile regression (CVQR)<n>CVQR combines neural optimal transport with quantized optimization, and apply it to predictions.
  arXiv  Detail & Related papers  (2025-09-29T19:50:19Z)
• A Trainable Optimizer [18.195022468462753]
  We present a framework that jointly trains the full gradient estimator and the trainable weights of the model.<n>Pseudo-linear TO incurs negligible computational overhead, requiring only minimal additional multiplications.<n> Experiments demonstrate that TO methods converge faster than benchmark algorithms.
  arXiv  Detail & Related papers  (2025-08-03T14:06:07Z)
• A Novel Unified Parametric Assumption for Nonconvex Optimization [53.943470475510196]
  Non optimization is central to machine learning, but the general framework non convexity enables weak convergence guarantees too pessimistic compared to the other hand.<n>We introduce a novel unified assumption in non convex algorithms.
  arXiv  Detail & Related papers  (2025-02-17T21:25:31Z)
• ENOT: Expectile Regularization for Fast and Accurate Training of Neural Optimal Transport [3.0237149871998095]
  We present a new approach to accurately and efficiently estimating optimal transportation plan. It is called ExpectileRegularised Neural Transport Optimal (ENOT) ENOT enforces binding conditions on the learning process of dual potentials.
  arXiv  Detail & Related papers  (2024-03-06T15:15:42Z)
• Efficient Neural Network Approaches for Conditional Optimal Transport with Applications in Bayesian Inference [1.740133468405535]
  We present two solutions of solutions of $D1450F454545454545454545454545454545454545454545454545454545454545454545454545454545454545454545454 5454545454545454545454545454545454545454545454545454545454545454545454545454545454545454545454545454 54545454545454545454545454545454545
  arXiv  Detail & Related papers  (2023-10-25T20:20:09Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods [75.34939761152587]
  Efficient computation of the optimal transport distance between two distributions serves as an algorithm that empowers various applications. This paper develops a scalable first-order optimization-based method that computes optimal transport to within $varepsilon$ additive accuracy.
  arXiv  Detail & Related papers  (2023-01-30T15:46:39Z)
• Neural Non-Rigid Tracking [26.41847163649205]
  We introduce a novel, end-to-end learnable, differentiable non-rigid tracker. We employ a convolutional neural network to predict dense correspondences and their confidences. Compared to state-of-the-art approaches, our algorithm shows improved reconstruction performance.
  arXiv  Detail & Related papers  (2020-06-23T18:00:39Z)
• Cogradient Descent for Bilinear Optimization [124.45816011848096]
  We introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent. Our algorithm is applied to solve problems with one variable under the sparsity constraint.
  arXiv  Detail & Related papers  (2020-06-16T13:41:54Z)

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.