arXiv Machine Learning
Aug 18
Priors learned from legacy reconstructions inherit undetectable overconfidence
arXiv:2607. 21721v3 Announce Type: replace-cross Abstract: Where truths are scarce (e.
Prior laundering: learned priors with inherited, undetectable overconfidence
arXiv:2607. 21721v1 Announce Type: cross Abstract: Learned generative priors are increasingly used for ill-posed Bayesian inverse problems, their posterior uncertainty treated as earned from data.
Related stories
arXiv Machine Learning
Jun 2
Measurement Geometry and Design for Trustworthy Generative Inverse Problems
arXiv:2606. 02309v1 Announce Type: new Abstract: Generative models are increasingly used as priors for inverse problems, but their ability to produce realistic images creates a basic trust problem: a plausible reconstruction may be supported by the measurements, or it may be filled in by the prior along unobserved directions.
arXiv Machine Learning
Jun 3
Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem Performance
arXiv:2601. 22443v2 Announce Type: replace Abstract: Can a diffusion model trained on bedrooms recover human faces?
arXiv Machine Learning
Sep 3
Source Distribution Estimation by Posterior Averaging
The paper introduces a new approach to source distribution estimation (SDE) in simulation-based science, addressing limitations of existing methods that rely on a fixed surrogate likelihood. By employing an expectation‑maximization framework, the authors iteratively train an amortized posterior on fresh simulations (E‑step) and refit the source distribution to the posterior’s average (M‑step). Two parameterizations are explored: separate source and posterior flows, and a single shared conditional flow, with experiments on three benchmark tasks showing improved performance over fixed surrogate and iterated baseline methods, notably achieving higher data‑space C2ST scores on the Lotka–Volterra benchmark.
arXiv Machine Learning
Jun 16
Exact Posterior Score Estimation for Solving Linear Inverse Problems
arXiv:2606. 17048v1 Announce Type: new Abstract: Diffusion and flow-based models learn powerful data priors by training a denoiser to reverse Gaussian corruption.
arXiv Machine Learning
Jun 30
A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems
arXiv:2606. 30230v1 Announce Type: cross Abstract: Learned reconstruction operators for inverse problems are typically trained under a fixed noise model, and generalize poorly when the distribution during testing differs from the one assumed during training.
Hugging Face Trending Papers
Jul 14
Exact and Calibrated Diffusion Reconstruction for Digital Breast Tomosynthesis
Limited-angle digital breast tomosynthesis (DBT) reconstructs a volume from a few low-dose projections over a narrow arc. At a representative nine-view, $25^{\circ}$ protocol more than 98% of image space is unmeasured, so a learned prior must supply structure in the missing wedge.
arXiv Machine Learning
Jun 2
Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates
arXiv:2606. 02331v1 Announce Type: cross Abstract: Diffusion-based inverse problem solvers can produce realistic reconstructions, but realism alone does not ensure that the recovered details are supported by the measurement.
arXiv Machine Learning
Aug 27
Continually learning neural-operator surrogate for three-dimensional airborne electromagnetic Bayesian inversion
The paper presents a continually learning neural‑operator surrogate for the three‑dimensional forward operator used in time‑domain airborne electromagnetic (AEM) Bayesian inversion. By training on successive geological priors and employing an ensemble‑disagreement validity check, the surrogate replaces the expensive forward solver, enabling the Markov chain Monte Carlo sampler to reproduce the full‑solver posterior with credible intervals within 2.6 % of the truth. Applied to the 2013 Capricorn TEMPEST survey, the surrogate inverts over two million soundings in seconds, making uncertainty‑quantified conductivity imaging at survey scale feasible for near real‑time mineral‑systems targeting.
arXiv Computer Vision
Sep 11
A Calibration Audit of Confidence in Feed-Forward 3D Reconstruction Models
The paper audits the confidence outputs of seven feed‑forward 3D reconstruction backbones across 13 datasets, evaluating four properties: error ranking, average error‑to‑uncertainty ratio, slope of this ratio, and coverage of the implied error distribution. While confidence ranks errors well, the decoded uncertainty is consistently too small—off by at least 2.4× on median cases—and worsens with higher confidence. A post‑hoc power‑law fit per backbone‑dataset pair improves all four metrics at the dataset level, reducing the median error by 1.35×, but fails to correct coverage for many held‑out scenes, indicating the models lack the correct error scale and distribution shape.
arXiv Machine Learning
Sep 14
Physical-State-Guided Diffusion Sampling for Full-Waveform Inversion
Physical-State-Guided Diffusion Sampling (PSG) couples a persistent physical velocity model to a diffusion prior via a Gaussian bridge, allowing the physical state to be refined by waveform fitting while guiding the reverse diffusion process. This approach separates wave‑equation and denoiser gradients, preserving conventional FWI initialization and optimization history. PSG outperforms classical and diffusion‑based baselines on four OpenFWI families, maintains strong structural recovery under noise, and supports large‑scale models like Marmousi, Overthrust, and BP2004 Salt without retraining.
arXiv Machine Learning
Jun 15
Decoupled Latent Optimization of Diffusion Models for Full Waveform Inversion
arXiv:2606. 14139v1 Announce Type: new Abstract: Full waveform inversion (FWI) recovers subsurface velocity from seismic recordings by solving a severely ill-posed, nonconvex PDE-constrained optimization.