arXiv Machine Learning By Caterina Amendola, Giulia Maffeis, Lorenzo Buffoni, Lorenzo Chicchi, Francesco Coghi, Duccio Fanelli, Raffaele Marino, Fabrizio Martelli, Riccardo Paoli, Lorenzo Pattelli, Lorenzo Spinelli

Learning-Based Reconstruction of Optical Properties in Bilayered Media from Single-distance Time-Resolved Reflectance Measurements

Read the original on arXiv Machine Learning →

The paper presents a machine‑learning framework for reconstructing absorption and scattering coefficients in bilayered biological media from single‑distance, time‑resolved reflectance data. By training on a synthetic dataset generated with exact Monte Carlo simulations, the method outperforms traditional diffusion‑equation‑based inverse solvers in both speed and accuracy. It also estimates the dimensionality of the parameter space without prior knowledge of the number of layers, and suggests that future work could further improve accuracy using multi‑distance data.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
5d ago

Score-based diffusion models for severely ill-posed problems in diffuse optical tomography

Score-based diffusion models, a recent framework for posterior sampling in Bayesian inverse problems, are applied to diffuse optical tomography (DOT), a highly ill‑posed boundary value problem for recovering tissue absorption and scattering. The authors introduce a mixed score that combines a learned component with a model‑based component, providing a theoretical justification for its local approximation to the true score in the small diffusion‑time regime. Four difference‑imaging approaches are compared—classical model‑based, approximate diffusion, exact posterior sampling (UCoS), and a regularized UCoS—showing that UCoS yields more accurate reconstructions, especially under limited‑view geometry and real experimental data.

By Fabian Schneider, Meghdoot Mozumder, Konstantin Tamarov, Leila Taghizadeh, Tanja Tarvainen, Tapio Helin, Duc-Lam Duong
arXiv Machine Learning
5d ago

PosteriorBench: From Point Estimates to Posterior Matching in Evaluating Generative Inverse Solvers

PosteriorBench is a new benchmark that evaluates how well generative inverse solvers recover full posterior distributions rather than just a single reconstruction. It tests four physics-based inverse problems—Darcy flow inversion, Poisson source recovery, carbon capture and storage, and light transport material inference—using high-fidelity reference posteriors generated by rejection sampling and MCMC. The benchmark employs five metrics (posterior-mean error, posterior-standard-deviation error, maximum mean discrepancy, sliced Wasserstein distance, and radially averaged power-spectrum error) to assess pointwise accuracy, uncertainty, distributional alignment, and global frequency fidelity, revealing significant distribution-matching gaps in current solvers and highlighting the importance of neural operators, guidance weights, and generation noise for posterior-variance calibration.

By Jiachen Yao, Zi-Siang Hsu, Xi Deng, Aditi Gupta, Xin Ju, Sally M Benson, Gege Wen, Anima Anandkumar
arXiv Machine Learning
Sep 3

Scalable Bayesian Optimization of Composite Functions for Image-Based Inverse Problems in Materials Characterization

The paper introduces Scalable Bayesian Optimization of Composite Functions (SBOCF) for efficiently estimating physical parameters from scientific images, specifically targeting electron microscopy PACBED patterns. SBOCF leverages the composite structure of the image-matching objective, reducing modeled outputs from 24,649 to 11 by using patch-level summaries and correction terms. With only 50 simulator evaluations, SBOCF outperformed standard Bayesian optimization, achieving up to 290× lower median SSE on synthetic SrTiO3 benchmarks and producing accurate parameter estimates on experimental data without task-specific pretraining.

By Dasol Yoon, Poompol Buathong, Chia-Hao Lee, Yujia Zhang, David A. Muller, Peter I. Frazier