Pith. sign in

REVIEW 5 cited by

Sampling in Unit Time with Kernel Fisher-Rao Flow

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2401.03892 v3 pith:6G564TZN submitted 2024-01-08 stat.CO cs.LGstat.ML

Aimee Maurais , Youssef Marzouk This is my paper · ORCID
classification stat.COcs.LGstat.ML
keywords mean-fielddensitysamplesequationfieldfisher-raoflowgradient-free
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We introduce a new mean-field ODE and corresponding interacting particle systems (IPS) for sampling from an unnormalized target density. The IPS are gradient-free, available in closed form, and only require the ability to sample from a reference density and compute the (unnormalized) target-to-reference density ratio. The mean-field ODE is obtained by solving a Poisson equation for a velocity field that transports samples along the geometric mixture of the two densities, which is the path of a particular Fisher-Rao gradient flow. We employ a RKHS ansatz for the velocity field, which makes the Poisson equation tractable and enables discretization of the resulting mean-field ODE over finite samples. The mean-field ODE can be additionally be derived from a discrete-time perspective as the limit of successive linearizations of the Monge-Amp\`ere equations within a framework known as sample-driven optimal transport. We introduce a stochastic variant of our approach and demonstrate empirically that our IPS can produce high-quality samples from varied target distributions, outperforming comparable gradient-free particle systems and competitive with gradient-based alternatives.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Generative Modeling via Kernelized Stochastic Interpolants

    cs.LG 2026-02 conditional novelty 6.0 of 10

    The drift of a stochastic interpolant is estimated by solving a P×P linear system from feature gradients, enabling training-free generation and training-free combination of pretrained generative models.

  2. Stable Derivative Free Gaussian Mixture Variational Inference for Bayesian Inverse Problems

    cs.LG 2025-01 conditional novelty 6.0 of 10

    DF-GMVI approximates Bayesian posteriors with Gaussian mixtures using derivative-free quadrature that preserves covariance positivity and affine invariance.

  3. An Eulerian approach to regularized JKO scheme with low-rank tensor decompositions for Bayesian inversion

    math.NA 2024-11 conditional novelty 6.0 of 10

    A tensor-train solver for the entropy-regularized JKO proximal step approximates Bayesian posteriors using only pointwise density evaluations, matching or beating Metropolis-Hastings in several tests.

  4. Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach

    cs.LG 2025-06 conditional novelty 5.0 of 10

    A weighted-particle sampler evolves the posterior through the diffusion model's reverse dynamics, with theoretical error bounds and improved image reconstructions.

  5. Path-Guided Particle-based Sampling

    cs.LG 2024-12 conditional novelty 5.0 of 10

    PGPS trains a neural velocity field to transport particles along a log-weighted shrinkage density path, giving a Wasserstein error bound of O(delta) + O(sqrt(h)) and improved mode seeking in Bayesian inference.

Pith tools