Entropic Riemannian Neural Optimal Transport

• URL: http://arxiv.org/abs/2605.04255v1
• Date: Tue, 05 May 2026 19:43:03 GMT
• Title: Entropic Riemannian Neural Optimal Transport
• Abstract summary: We propose a unified framework that combines intrinsic entropic OT and amortized out-of-sample evaluation.<n>Our method matches or improves over Euclidean, tangent-space, and log-Euclidean baselines on benchmarks over $mathbbS2$, $mathrmSO(3)$, $mathrmSPD(3)$, $mathrmSE(3)$, and $mathbbH2$.
• Score: 41.69130102668252
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many machine learning problems involve data supported on curved spaces such as spheres, rotation groups, hyperbolic spaces, and general Riemannian manifolds, where Euclidean geometry can distort distances, averages, and the resulting optimal transport (OT) problem. Existing manifold OT methods have pursued amortized out-of-sample maps, while entropic regularization has made discrete OT more scalable, but these advantages have remained largely disjoint. We propose Entropic Riemannian Neural Optimal Transport (Entropic RNOT), a unified framework that combines intrinsic entropic OT with amortized out-of-sample evaluation on Riemannian manifolds. Our method learns a single target-side Schrödinger potential through a neural pullback parameterization, recovers the induced Gibbs coupling, and uses the resulting conditional laws to construct intrinsic transport surrogates. These include barycentric projections on Cartan-Hadamard manifolds and heat-smoothed conditional surrogates on stochastically complete manifolds, the latter turning possibly atomic target laws into absolutely continuous ones. For fixed regularization $\varepsilon>0$, we prove that the proposed hypothesis class recovers the entropic optimal coupling in strong probabilistic metrics. As consequences, barycentric surrogates converge in $L^2$, while heat-smoothed surrogates are stable at fixed heat time and asymptotically unbiased as the heat time vanishes. The guarantees hold for compactly supported data on possibly noncompact manifolds. Empirically, our method matches or improves over Euclidean, tangent-space, and log-Euclidean baselines on benchmarks over $\mathbb{S}^2$, $\mathrm{SO}(3)$, $\mathrm{SPD}(3)$, $\mathrm{SE}(3)$, and $\mathbb{H}^2$, scales favorably relative to discrete manifold Sinkhorn, and in a protein-ligand docking application, refines poses on $\mathrm{SE}(3)$ without retraining or per-instance optimization.

Related papers

• Curvature-Independent Regret Bounds for Distributed Online Optimization on Hadamard Manifolds [9.035866986287205]
  This work addresses decentralized online convexian optimization on Hadamard.<n>To our knowledge these are the first curvature-independent regret guarantees on embeddings for predicted rates, with no degradation due to curvature.
  arXiv  Detail & Related papers  (2026-09-12T01:53:49Z)
• Is Spurious Correlation Removal Always Learnable? [56.28155520961125]
  Invariant learning can fail even when the structure is statistically identifiable.<n>We show a conditional computational barrier: under a black-box samplable supervised sparse recovery primitive, there exist emphamplable multi-dimensional environments.<n>Synthetic and real datasets illustrate the predicted gaps and transitions and motivate simple diversity diagnostics.
  arXiv  Detail & Related papers  (2026-06-11T05:49:43Z)
• Quadratically Regularized Optimal Transport: Localization Bounds and Affine Case Analysis [4.280045284812897]
  We show that the support of the QOT cannot concentrate around the Monge graph faster than order $varepsilonfrac1d+2$ in the directed Hausdorff distance.<n>We derive a sharp pointwise tube bound of order $varepsilonfrac1d+2$ by reducing the problem to self-transport and applying recent self-transport sparsity results.
  arXiv  Detail & Related papers  (2026-05-23T16:21:03Z)
• $Z^2$-Sampling: Zero-Cost Zigzag Trajectories for Semantic Alignment in Diffusion Models [6.21141073537668]
  Implicit Z-Sampling proves that intermediate states can be algebraically annihilated via operator dualities.<n>$Z2$-Sampling couples implicit algebraic collapse with a dynamically cached Temporal Semantic Surrogate.
  arXiv  Detail & Related papers  (2026-04-26T05:16:54Z)
• Riemannian gradient descent for Hartree-Fock theory [0.0]
  We present an optimization framework for Hartree-Fock theory formulated directly in the Sobolev space $H1$.<n>Explicit expressions for Euclidean and Riemannian gradients, tangent-space projections, and retractions are derived.<n>The proposed formulation provides a geometrically consistent and discretization-independent perspective on electronic structure optimization.
  arXiv  Detail & Related papers  (2026-03-16T19:58:42Z)
• Optimal Transportation and Alignment Between Gaussian Measures [80.4634530260329]
  Optimal transport (OT) and Gromov-Wasserstein (GW) alignment provide interpretable geometric frameworks for datasets.<n>Because these frameworks are computationally expensive, large-scale applications often rely on closed-form solutions for Gaussian distributions under quadratic cost.<n>This work provides a comprehensive treatment of Gaussian, quadratic cost OT and inner product GW (IGW) alignment, closing several gaps in the literature to broaden applicability.
  arXiv  Detail & Related papers  (2025-12-03T09:01:48Z)
• Online Optimization on Hadamard Manifolds: Curvature Independent Regret Bounds on Horospherically Convex Objectives [9.940555460165545]
  We analyze the geodesicity framework (g-ity) for h-in-variants of the curvature manifold.<n>In particular, we investigate the application of a Fr-in-variant with the definite (SPD) with a gradient.
  arXiv  Detail & Related papers  (2025-09-14T12:27:31Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Last-Iterate Convergence of Adaptive Riemannian Gradient Descent for Equilibrium Computation [52.73824786627612]
  This paper establishes new convergence results for textitgeodesic strongly monotone games.<n>Our key result shows that RGD attains last-iterate linear convergence in a textitgeometry-agnostic fashion.<n>Overall, this paper presents the first geometry-agnostic last-iterate convergence analysis for games beyond the Euclidean settings.
  arXiv  Detail & Related papers  (2023-06-29T01:20:44Z)
• Optimal policy evaluation using kernel-based temporal difference methods [78.83926562536791]
  We use kernel Hilbert spaces for estimating the value function of an infinite-horizon discounted Markov reward process. We derive a non-asymptotic upper bound on the error with explicit dependence on the eigenvalues of the associated kernel operator. We prove minimax lower bounds over sub-classes of MRPs.
  arXiv  Detail & Related papers  (2021-09-24T14:48:20Z)
• Nonparametric approximation of conditional expectation operators [0.3655021726150368]
  We investigate the approximation of the $L2$-operator defined by $[Pf](x) := mathbbE[ f(Y) mid X = x ]$ under minimal assumptions. We prove that $P$ can be arbitrarily well approximated in operator norm by Hilbert-Schmidt operators acting on a reproducing kernel space.
  arXiv  Detail & Related papers  (2020-12-23T19:06:12Z)
• Debiased Sinkhorn barycenters [110.79706180350507]
  Entropy regularization in optimal transport (OT) has been the driver of many recent interests for Wasserstein metrics and barycenters in machine learning. We show how this bias is tightly linked to the reference measure that defines the entropy regularizer. We propose debiased Wasserstein barycenters that preserve the best of both worlds: fast Sinkhorn-like iterations without entropy smoothing.
  arXiv  Detail & Related papers  (2020-06-03T23:06:02Z)

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.