PaperSwipe

The Loss Landscape of Powder X-Ray Diffraction-Based Structure Optimization Is Too Rough for Gradient Descent

Published 2 days agoVersion 1arXiv:2512.04036

Authors

Nofit Segal, Akshay Subramanian, Mingda Li, Benjamin Kurt Miller, Rafael Gomez-Bombarelli

Categories

cond-mat.mtrl-scics.CE

Abstract

Solving crystal structures from powder X-ray diffraction (XRD) is a central challenge in materials characterization. In this work, we study the powder XRD-to-structure mapping using gradient descent optimization, with the goal of recovering the correct structure from moderately distorted initial states based solely on XRD similarity. We show that commonly used XRD similarity metrics result in a highly non-convex landscape, complicating direct optimization. Constraining the optimization to the ground-truth crystal family significantly improves recovery, yielding higher match rates and increased mutual information and correlation scores between structural similarity and XRD similarity. Nevertheless, the landscape may remain non-convex along certain symmetry axes. These findings suggest that symmetry-aware inductive biases could play a meaningful role in helping learning models navigate the inverse mapping from diffraction to structure.

The Loss Landscape of Powder X-Ray Diffraction-Based Structure Optimization Is Too Rough for Gradient Descent

2 days ago
v1
5 authors

Categories

cond-mat.mtrl-scics.CE

Abstract

Solving crystal structures from powder X-ray diffraction (XRD) is a central challenge in materials characterization. In this work, we study the powder XRD-to-structure mapping using gradient descent optimization, with the goal of recovering the correct structure from moderately distorted initial states based solely on XRD similarity. We show that commonly used XRD similarity metrics result in a highly non-convex landscape, complicating direct optimization. Constraining the optimization to the ground-truth crystal family significantly improves recovery, yielding higher match rates and increased mutual information and correlation scores between structural similarity and XRD similarity. Nevertheless, the landscape may remain non-convex along certain symmetry axes. These findings suggest that symmetry-aware inductive biases could play a meaningful role in helping learning models navigate the inverse mapping from diffraction to structure.

Authors

Nofit Segal, Akshay Subramanian, Mingda Li et al. (+2 more)

arXiv ID: 2512.04036
Published Dec 3, 2025

Click to preview the PDF directly in your browser