The Advective Fisher-Rao Geometry of Deterministic Measure Transport

• URL: http://arxiv.org/abs/2608.12111v1
• Date: Wed, 12 Aug 2026 14:32:31 GMT
• Title: The Advective Fisher-Rao Geometry of Deterministic Measure Transport
• Abstract summary: A novel advective Fisher-Rao metric is introduced for optimization tasks on paths of probability measures governed by the continuity equation.<n>Here, we demonstrate empirically that the advective Fisher-Rao metric yields the desired optimal fitting of probability densities, whereas the Gauss--Newton method yields optimal fitting of velocity fields.
• Score: 3.3217545377155027
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A novel advective Fisher-Rao metric is introduced for optimization tasks on paths of probability measures governed by the continuity equation. This metric is shown to lead to optimal descent directions. It is then shown that this metric arises naturally from three different perspectives: As the rescaled zero-noise limit of the Fisher-Rao metric on path measures, as the expected value of the second variation of the Freidlin--Wentzell large deviation rate functional, and as the Hessian of the Benamou--Brenier action functional from dynamic optimal transport. We supplement this geometric construction with computational experiments. Here, we demonstrate empirically that the advective Fisher-Rao metric yields the desired optimal fitting of probability densities, whereas the Gauss--Newton method yields optimal fitting of velocity fields.

Related papers

• FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers [7.108048394322025]
  Activation steering methods modify intermediate representations of language models to control output behavior, but universally assume the activation space is Euclidean.<n>We show this assumption fails drastically: the local geometry induced by the model's own output behavior deviates from the Euclidean metric by over 97% in relative spectral norm on GPT-2.
  arXiv  Detail & Related papers  (2026-05-17T03:00:16Z)
• Inversion-Free Natural Gradient Descent on Riemannian Manifolds [5.556612138252781]
  This paper proposes an inversion-free natural gradient method for probability distributions with convex parameters.<n>The manifold setting offers several advantages: one can implicitly enforce parameter constraints.<n>A limited-memory variant of the algorithm with sub-quadratic storage complexity is proposed.
  arXiv  Detail & Related papers  (2026-04-03T11:08:59Z)
• 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)
• Surrogate Modelling of Proton Dose with Monte Carlo Dropout Uncertainty Quantification [0.0]
  We develop a neural surrogate that integrates Monte Carlo dropout to provide fast, differentiable dose predictions.<n>The approach achieves significant speedups over MC while retaining uncertainty information.<n>It is suitable for integration into robust planning, adaptive replanning and uncertainty-aware optimisation in proton therapy.
  arXiv  Detail & Related papers  (2025-09-16T19:54:49Z)
• Statistical Inference for Temporal Difference Learning with Linear Function Approximation [55.80276145563105]
  We investigate the statistical properties of Temporal Difference learning with Polyak-Ruppert averaging.<n>We make three theoretical contributions that improve upon the current state-of-the-art results.
  arXiv  Detail & Related papers  (2024-10-21T15:34:44Z)
• 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)
• Approximation and bounding techniques for the Fisher-Rao distances between parametric statistical models [7.070726553564701]
  We consider several numerically robust approximation and bounding techniques for the Fisher-Rao distances.<n>In particular, we obtain a generic method to guarantee an arbitrarily small additive error on the approximation.<n>We propose two new distances based either on the Fisher-Rao lengths of curves serving as proxies of Fisher-Rao geodesics.
  arXiv  Detail & Related papers  (2024-03-15T08:05:16Z)
• The Fisher-Rao geometry of CES distributions [50.50897590847961]
  The Fisher-Rao information geometry allows for leveraging tools from differential geometry. We will present some practical uses of these geometric tools in the framework of elliptical distributions.
  arXiv  Detail & Related papers  (2023-10-02T09:23:32Z)
• Warped geometric information on the optimisation of Euclidean functions [43.43598316339732]
  We consider optimisation of a real-valued function defined in a potentially high-dimensional Euclidean space. We find the function's optimum along a manifold with a warped metric. Our proposed algorithm, using 3rd-order approximation of geodesics, tends to outperform standard Euclidean gradient-based counterparts.
  arXiv  Detail & Related papers  (2023-08-16T12:08:50Z)
• Stochastic Marginal Likelihood Gradients using Neural Tangent Kernels [78.6096486885658]
  We introduce lower bounds to the linearized Laplace approximation of the marginal likelihood. These bounds are amenable togradient-based optimization and allow to trade off estimation accuracy against computational complexity.
  arXiv  Detail & Related papers  (2023-06-06T19:02:57Z)
• Variational Transport: A Convergent Particle-BasedAlgorithm for Distributional Optimization [106.70006655990176]
  A distributional optimization problem arises widely in machine learning and statistics. We propose a novel particle-based algorithm, dubbed as variational transport, which approximately performs Wasserstein gradient descent. We prove that when the objective function satisfies a functional version of the Polyak-Lojasiewicz (PL) (Polyak, 1963) and smoothness conditions, variational transport converges linearly.
  arXiv  Detail & Related papers  (2020-12-21T18:33:13Z)

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.