Conditional Flow Matching for Bayesian Posterior Inference

• URL: http://arxiv.org/abs/2510.09534v2
• Date: Wed, 15 Oct 2025 14:51:36 GMT
• Title: Conditional Flow Matching for Bayesian Posterior Inference
• Authors: So Won Jeong, Percy S. Zhai, Veronika Ročková,
• Abstract summary: We propose a generative multivariate posterior sampler via flow matching.<n>It offers a simple training objective, and does not require access to likelihood evaluation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a generative multivariate posterior sampler via flow matching. It offers a simple training objective, and does not require access to likelihood evaluation. The method learns a dynamic, block-triangular velocity field in the joint space of data and parameters, which results in a deterministic transport map from a source distribution to the desired posterior. The inverse map, named vector rank, is accessible by reversibly integrating the velocity over time. It is advantageous to leverage the dynamic design: proper constraints on the velocity yield a monotone map, which leads to a conditional Brenier map, enabling a fast and simultaneous generation of Bayesian credible sets whose contours correspond to level sets of Monge-Kantorovich data depth. Our approach is computationally lighter compared to GAN-based and diffusion-based counterparts, and is capable of capturing complex posterior structures. Finally, frequentist theoretical guarantee on the consistency of the recovered posterior distribution, and of the corresponding Bayesian credible sets, is provided.

Related papers

• A Long-Short Flow-Map Perspective for Drifting Models [10.305612650249804]
  We show that a global transport process can be decomposed into a long-horizon flow map followed by a short-time terminal flow map.<n>We propose a new likelihood learning formulation that aligns the long-short flow-map decomposition with density evolution under transport.
  arXiv  Detail & Related papers  (2026-02-24T01:48:52Z)
• Learnable Chernoff Baselines for Inference-Time Alignment [64.81256817158851]
  We introduce Learnable Chernoff Baselines as a method for efficiently and approximately sampling from exponentially tilted kernels.<n>We establish total-variation guarantees to the ideal aligned model, and demonstrate in both continuous and discrete diffusion settings that LCB sampling closely matches ideal rejection sampling.
  arXiv  Detail & Related papers  (2026-02-08T00:09:40Z)
• Accelerated Sequential Flow Matching: A Bayesian Filtering Perspective [16.29333060724397]
  We introduce Sequential Flow Matching, a principled framework grounded in Bayesian filtering.<n>By treating streaming inference as learning a probability flow that transports the predictive distribution from one time step to the next, our approach naturally aligns with the structure of Bayesian belief updates.<n>Our method achieves performance competitive with full-step diffusion while requiring only one or very few sampling steps, therefore with faster sampling.
  arXiv  Detail & Related papers  (2026-02-05T05:37:14Z)
• Tilt Matching for Scalable Sampling and Fine-Tuning [4.14348726233299]
  We propose a scalable algorithm for using interpolants to sample from unnormalized densities and for fine-tuning generative models.<n>The approach, Tilt Matching, arises from a dynamical equation relating the flow matching velocity to one targeting the same distribution tilted by a reward.<n>We empirically verify that the approach is efficient and highly scalable, providing state-of-the-art results on sampling under Lennard-Jones potentials and is competitive on fine-tuning Stable Diffusion.
  arXiv  Detail & Related papers  (2025-12-26T02:12:10Z)
• Test-time scaling of diffusions with flow maps [68.79792714591564]
  A common recipe to improve diffusion models at test-time is to introduce the gradient of the reward into the dynamics of the diffusion itself.<n>We propose a simple solution by working directly with a flow map.<n>By exploiting a relationship between the flow map and velocity field governing the instantaneous transport, we construct an algorithm, Flow Map Trajectory Tilting (FMTT), which provably performs better ascent on the reward than standard test-time methods.
  arXiv  Detail & Related papers  (2025-11-27T18:44:12Z)
• Neural Triangular Transport Maps: A New Approach Towards Sampling in Lattice QCD [0.7161783472741748]
  We introduce a comprehensive framework for triangular transport maps that navigates the fundamental trade-off between emphexact sparsity and emphapproximate sparsity<n>Using $phi4$ in two dimensions as a controlled setting, we analyze how node labelings (orderings) affect the sparsity and performance of triangular maps.
  arXiv  Detail & Related papers  (2025-10-15T03:15:10Z)
• Solving High-dimensional Inverse Problems Using Amortized Likelihood-free Inference with Noisy and Incomplete Data [43.43717668587333]
  We present a likelihood-free probabilistic inversion method based on normalizing flows for high-dimensional inverse problems.<n>The proposed method is composed of two complementary networks: a summary network for data compression and an inference network for parameter estimation.<n>We apply the proposed method to an inversion problem in groundwater hydrology to estimate the posterior distribution of the log-conductivity field conditioned on spatially sparse time-series observations.
  arXiv  Detail & Related papers  (2024-12-05T19:13:17Z)
• KL-geodesics flow matching with a novel sampling scheme [4.347494885647007]
  Non-autoregressive language models generate all tokens simultaneously, offering potential speed advantages over traditional autoregressive models.<n>We investigate a conditional flow matching approach for text generation.
  arXiv  Detail & Related papers  (2024-11-25T17:15:41Z)
• Back-Projection Diffusion: Solving the Wideband Inverse Scattering Problem with Diffusion Models [2.717354728562311]
  We present Wideband Back-Projection Diffusion, an end-to-end probabilistic framework for approximating the posterior distribution induced by the inverse scattering map from wideband scattering data.<n>This framework produces highly accurate reconstructions, leveraging conditional diffusion models to draw samples, and also honors the symmetries of the underlying physics of wave-propagation.
  arXiv  Detail & Related papers  (2024-08-05T23:33:24Z)
• MomentDiff: Generative Video Moment Retrieval from Random to Real [71.40038773943638]
  We provide a generative diffusion-based framework called MomentDiff. MomentDiff simulates a typical human retrieval process from random browsing to gradual localization. We show that MomentDiff consistently outperforms state-of-the-art methods on three public benchmarks.
  arXiv  Detail & Related papers  (2023-07-06T09:12:13Z)
• Density Ratio Estimation via Infinitesimal Classification [85.08255198145304]
  We propose DRE-infty, a divide-and-conquer approach to reduce Density ratio estimation (DRE) to a series of easier subproblems. Inspired by Monte Carlo methods, we smoothly interpolate between the two distributions via an infinite continuum of intermediate bridge distributions. We show that our approach performs well on downstream tasks such as mutual information estimation and energy-based modeling on complex, high-dimensional datasets.
  arXiv  Detail & Related papers  (2021-11-22T06:26:29Z)
• Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases [131.50372468579067]
  We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. We represent the reconstructed surfaces as atlases computed by a neural network, which enables us to establish correspondences between frames. Our approach outperforms state-of-the-art ones on several challenging datasets.
  arXiv  Detail & Related papers  (2021-11-12T17:48:25Z)
• Deep Shells: Unsupervised Shape Correspondence with Optimal Transport [52.646396621449]
  We propose a novel unsupervised learning approach to 3D shape correspondence. We show that the proposed method significantly improves over the state-of-the-art on multiple datasets.
  arXiv  Detail & Related papers  (2020-10-28T22:24:07Z)
• Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation [72.40827239394565]
  We propose to compute features only at sparsely sampled locations. We then densely reconstruct the feature map with an efficient procedure. The presented network is experimentally shown to save substantial computation while maintaining accuracy over a variety of computer vision tasks.
  arXiv  Detail & Related papers  (2020-03-19T15:36:31Z)

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.