An operator splitting analysis of Wasserstein--Fisher--Rao gradient flows
Not on the map. Why?
Abstract (arXiv)
Wasserstein-Fisher-Rao (WFR) gradient flows have been recently proposed as a powerful sampling tool that combines the advantages of pure Wasserstein (W) and pure Fisher-Rao (FR) gradient flows. Existing algorithmic developments implicitly make use of operator splitting techniques to numerically approximate the WFR partial differential equation, whereby the W flow is evaluated over a given step size and then the FR flow (or vice versa). This works investigates the impact of the order in which the W and FR operator are evaluated and aims to provide a quantitative analysis. Somewhat surprisingly, we show that with a judicious choice of step size and operator ordering, the split scheme can converge to the target distribution faster than the exact WFR flow (in terms of model time). We obtain variational formulae describing the evolution over one time step of both splitting schemes and investigate in which settings the W-FR split should be preferred to the FR-W split. As a step towards this goal we show that the WFR gradient flow preserves log-concavity and obtain the first sharp decay bound for WFR flow.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 26 of its 60 references that are in the map. First posted on arXiv 22 Nov 2025.
Builds on
26 of 60 references.
References · 26
- 2015Optimal Entropy-Transport problems and a new Hellinger-Kantorovich distance between positive measurescited by 138
- 2018Analysis of Langevin Monte Carlo via convex optimizationcited by 126
- 2018Sampling as optimization in the space of measures: The Langevin dynamics as a composite optimization problemcited by 123
- 2019Accelerating Langevin Sampling with Birth-deathcited by 45
- 2019High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithmcited by 36
- 2022Birth-death dynamics for sampling: Global convergence, approximations and their asymptoticscited by 30
- 2024Sampling in Unit Time with Kernel Fisher-Rao Flowcited by 27
- 2023Sampling via Gradient Flows in the Space of Probability Measurescited by 20
- 2019Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Ratescited by 17
- 2023An Explicit Expansion of the Kullback-Leibler Divergence along its Fisher-Rao Gradient Flowcited by 16
- 2023A connection between Tempering and Entropic Mirror Descentcited by 16
- 2021Adaptive Importance Sampling meets Mirror Descent: a Bias-variance tradeoffcited by 13
14 more
- 2024Fisher-Rao Gradient Flow: Geodesic Convexity and Functional Inequalitiescited by 13
- 2017Gradient Flows in Filtering and Fisher-Rao Geometrycited by 12
- 2024Measure transport with kernel mean embeddingscited by 11
- 2024Stein transport for Bayesian inferencecited by 11
- 2024Efficient, Multimodal, and Derivative-Free Bayesian Inference With Fisher-Rao Gradient Flowscited by 9
- 2017Nonreversible Langevin Samplers: Splitting Schemes, Analysis and Implementationcited by 8
- 2023Unbiased Kinetic Langevin Monte Carlo with Inexact Gradientscited by 8
- 2020McKean-Vlasov SDEs in nonlinear filteringcited by 7
- 2024Characterizing Dependence of Samples along the Langevin Dynamics and Algorithms via Contraction of Phi-Mutual Informationcited by 5
- 2025Sequential Monte Carlo approximations of Wasserstein--Fisher--Rao gradient flowscited by 5
- 2024Connections between sequential Bayesian inference and evolutionary dynamicscited by 4
- 2025A note on the unique properties of the Kullback--Leibler divergence for sampling via gradient flowscited by 4
- 2025Evolution of Gaussians in the Hellinger-Kantorovich-Boltzmann gradient flowcited by 3
- 2025Tuning-Free Sampling via Optimization on the Space of Probability Measurescited by 1
Built on by
Citing papers per year: 2026: 2.
2 papers.