analiza aiqbench
This arXiv preprint proposes latent annealed posterior sampling (LAPS), which combines a DeepONet-style Branch/Trunk decoder, flow-matching priors, and annealed likelihood incorporation for inferring random fields from sparse data. The reported results are benchmark-only, on two Gaussian cases, a bimodal problem, and a 2D Navier-Stokes field, so claims about real-world generalization remain untested. Readers working on uncertainty quantification or scientific ML should note the near-constant evaluation cost across grid resolutions, since that is the main practical claim.
Latent Annealed Posterior Sampling with a Variance-Preserving Bridge for Sparsely Observed Random Fields
arXiv:2610.20659v1 Announce Type: cross Abstract: Posterior inference for random fields from sparse observations presents two major challenges: accurately characterizing complex spatial uncertainty and preventing conditional sampling costs from growing substantially as the spatial grid is refined. To address these challenges, we propose latent annealed posterior sampling (LAPS). LAPS first maps the random field into a latent space with reduced dimensionality, while a coordinate decoder composed of Branch and Trunk networks enables field evaluation at arbitrary spatial locations. Flow matching is then used to learn the latent prior distribution. Based on this learned prior, posterior sampling is performed entirely in the latent space, with the observation likelihood incorporated progressively through an annealing procedure. To control local covariance inflation, we introduce a variance-preserving (VP) bridge that allocates a covariance budget between the transported latent state and a Gaussian perturbation. Numerical experiments demonstrate that LAPS accurately approximates posterior distributions, preserves distinct posterior modes, and reduces the dependence of conditional sampling costs on spatial resolution. Across two Gaussian benchmarks, LAPS attains small errors against exact posterior references, with sliced Wasserstein distances only 2 to 3 percent higher than the reference values obtained from exact posterior samples. In a bimodal posterior problem, LAPS reduces the sliced Wasserstein distance from 0.2693 to 0.1499 and consistently recovers both modes across all test scenarios. For a two dimensional Navier-Stokes random field, LAPS substantially improves marginal posterior calibration, while its evaluation time remains nearly constant as the output grid is refined from 64^2 to 512^2. These results demonstrate that LAPS achieves a favorable tradeoff among posterior accuracy, uncertainty calibration, and computational efficiency.
Abstract:Posterior inference for random fields from sparse observations presents two major challenges: accurately characterizing complex spatial uncertainty and preventing conditional sampling costs from growing substantially as the spatial grid is refined. To address these challenges, we propose latent annealed posterior sampling (LAPS). LAPS first maps the random field into a latent space with reduced dimensionality, while a coordinate decoder composed of Branch and Trunk networks enables field evaluation at arbitrary spatial locations. Flow matching is then used to learn the latent prior distribution. Based on this learned prior, posterior sampling is performed entirely in the latent space, with the observation likelihood incorporated progressively through an annealing procedure. To control local covariance inflation, we introduce a variance-preserving (VP) bridge that allocates a covariance budget between the transported latent state and a Gaussian perturbation. Numerical experiments demonstrate that LAPS accurately approximates posterior distributions, preserves distinct posterior modes, and reduces the dependence of conditional sampling costs on spatial resolution. Across two Gaussian benchmarks, LAPS attains small errors against exact posterior references, with sliced Wasserstein distances only 2 to 3 percent higher than the reference values obtained from exact posterior samples. In a bimodal posterior problem, LAPS reduces the sliced Wasserstein distance from 0.2693 to 0.1499 and consistently recovers both modes across all test scenarios. For a two dimensional Navier-Stokes random field, LAPS substantially improves marginal posterior calibration, while its evaluation time remains nearly constant as the output grid is refined from 64^2 to 512^2. These results demonstrate that LAPS achieves a favorable tradeoff among posterior accuracy, uncertainty calibration, and computational efficiency.
Machine Learning (stat.ML); Machine Learning (cs.LG)
arXiv:2610.20659 [stat.ML]
(or arXiv:2610.20659v1 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2610.20659 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 355 cuvinte
Subiecte conexe
Posterior-Averaged Bellman Flow Matching for Distributional Critics
arXiv · 15 oct. 2026
Annealed L\'{e}vy Diffusion via Gaussian Surrogate Reverse Dynamics
arXiv · 15 oct. 2026
Unsupervised Brain Anomaly Detection as a Bayesian Inverse Problem with Diffusion Prior
arXiv · 22 sept. 2026
Developing Distance-Aware Physics-Constrained Probabilistic Frameworks for Industrial Prognostics
arXiv · 9 iun. 2026