Rate-Optimal Noise Annealing in Semi-Dual Neural Optimal Transport: Tangential Identifiability, Off-Manifold Ambiguity, and Guaranteed Recovery

• URL: http://arxiv.org/abs/2602.04110v1
• Date: Wed, 04 Feb 2026 00:49:38 GMT
• Title: Rate-Optimal Noise Annealing in Semi-Dual Neural Optimal Transport: Tangential Identifiability, Off-Manifold Ambiguity, and Guaranteed Recovery
• Abstract summary: Semi-dual neural optimal transport learns a transport map via a max-min objective, yet training can converge to incorrect or degenerate maps.<n>We study additive-noise smoothing as a remedy and prove new map recovery guarantees as the noise vanishes.
• Score: 12.515121834321633
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semi-dual neural optimal transport learns a transport map via a max-min objective, yet training can converge to incorrect or degenerate maps. We fully characterize these spurious solutions in the common regime where data concentrate on low-dimensional manifold: the objective is underconstrained off the data manifold, while the on-manifold transport signal remains identifiable. Following Choi, Choi, and Kwon (2025), we study additive-noise smoothing as a remedy and prove new map recovery guarantees as the noise vanishes. Our main practical contribution is a computable terminal noise level $\varepsilon_{\mathrm{stat}}(N)$ that attains the optimal statistical rate, with scaling governed by the intrinsic dimension $m$ of the data. The formula arises from a theoretical unified analysis of (i) quantitative stability of optimal plans, (ii) smoothing-induced bias, and (iii) finite-sample error, yielding rates that depend on $m$ rather than the ambient dimension. Finally, we show that the reduced semi-dual objective becomes increasingly ill-conditioned as $\varepsilon \downarrow 0$. This provides a principled stopping rule: annealing below $\varepsilon_{\mathrm{stat}}(N)$ can $\textit{worsen}$ optimization conditioning without improving statistical accuracy.

Related papers

• From Atoms to Entropy: Optimal Noise Allocation for Diffusion Training in the Convex Regime [52.459513910242485]
  We develop a general statistical framework for studying optimal noise-level allocation in diffusion training.<n>We show that the optimized training schedule admits an atomic minimizer, concentrated on finitely many noise levels.<n>We then evaluate the entropic schedule in larger-scale experiments, where full schedule optimization is currently intractable.
  arXiv  Detail & Related papers  (2026-07-10T20:59:06Z)
• Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning [61.07540493350384]
  Self-distillation (SD) is the process of retraining a student on a mixture of ground-truth and the teacher's own predictions.<n>We show that for any prediction risk, the optimally mixed student improves upon the ridge teacher for every regularization level.<n>We propose a consistent one-shot tuning method to estimate $star$ without grid search, sample splitting, or refitting.
  arXiv  Detail & Related papers  (2026-02-19T17:21:15Z)
• Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate [33.30496814734325]
  Gradient Descent (SGD) based solvers have demonstrated strong empirical performance in recent machine learning applications.<n>We show that SGD methods can estimate the OT map with a minimax convergence rate of $mathcalO (1/sqrtn)$.<n>We identify a suitable projection set that contains a minimizer of the objective, even when the source measure is not compactly supported.
  arXiv  Detail & Related papers  (2025-10-29T08:43:19Z)
• 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)
• A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization [90.87444114491116]
  This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparametricized two-layer neural networks. We address (i) the convergence of the gradient descent-ascent algorithm and (ii) the representation learning of the neural networks. Results show that the feature representation induced by the neural networks is allowed to deviate from the initial one by the magnitude of $O(alpha-1)$, measured in terms of the Wasserstein distance.
  arXiv  Detail & Related papers  (2024-04-18T16:46:08Z)
• Normalizing flows as approximations of optimal transport maps via linear-control neural ODEs [49.1574468325115]
  We consider the problem of recovering the $Wimat$-optimal transport map T between absolutely continuous measures $mu,nuinmathcalP(mathbbRn)$ as the flow of a linear-control neural ODE.
  arXiv  Detail & Related papers  (2023-11-02T17:17:03Z)
• High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise [59.25598762373543]
  We show that wetailed high-prob convergence guarantees of learning on streaming data in the presence of heavy-tailed noise. We demonstrate analytically and that $ta$ can be used to the preferred choice of setting for a given problem.
  arXiv  Detail & Related papers  (2023-10-28T18:53:41Z)
• On Kinetic Optimal Probability Paths for Generative Models [42.12806492124782]
  Recent successful generative models are trained by fitting a neural network to an a-priori defined tractable probability density path taking noise to training examples. In this paper we investigate the space of Gaussian probability paths, which includes diffusion paths as an instance, and look for an optimal member in some useful sense.
  arXiv  Detail & Related papers  (2023-06-11T08:54:12Z)
• Achieving the Asymptotically Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach [36.88301225561535]
  offline reinforcement learning aims to learn from pre-collected datasets without active exploration. Existing approaches adopt a pessimistic stance towards uncertainty by penalizing rewards of under-explored state-action pairs to estimate value functions conservatively. We show that the distributionally robust optimization (DRO) based approach can also address these challenges and is asymptotically minimax optimal
  arXiv  Detail & Related papers  (2023-05-22T17:50:18Z)
• Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets [101.5329678997916]
  We study episodic two-player zero-sum Markov games (MGs) in the offline setting. The goal is to find an approximate Nash equilibrium (NE) policy pair based on a dataset collected a priori.
  arXiv  Detail & Related papers  (2022-02-15T15:39:30Z)
• Distributed Sparse Regression via Penalization [5.990069843501885]
  We study linear regression over a network of agents, modeled as an undirected graph (with no centralized node) The estimation problem is formulated as the minimization of the sum of the local LASSO loss functions plus a quadratic penalty of the consensus constraint. We show that the proximal-gradient algorithm applied to the penalized problem converges linearly up to a tolerance of the order of the centralized statistical error.
  arXiv  Detail & Related papers  (2021-11-12T01:51:50Z)
• Semi-Discrete Optimal Transport: Hardness, Regularization and Numerical Solution [8.465228064780748]
  We prove that computing the Wasserstein distance between a discrete probability measure supported on two points is already #P-hard. We introduce a distributionally robust dual optimal transport problem whose objective function is smoothed with the most adverse disturbance distributions. We show that smoothing the dual objective function is equivalent to regularizing the primal objective function.
  arXiv  Detail & Related papers  (2021-03-10T18:53:59Z)

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.